Decoupled Multifunctional Sensors for Personal Healthcare Monitoring
The important vital signs of a human body are respiration, temperature, pulse rate etc. Real time smartphone integrated monitoring and interpretation of such important vital signs will definitely offer healthcare professionals to take informed decisions beforehand. One of the ways to offer solution is the fabrication of multifunctional sensors which can sense breath, pressure, and temperature. However, cross sensitivity between the various external stimuli prevents accurate measurements of the target input signals when multiple of them are simultaneously applied. Hence it becomes vitally important to exploit the multimodal sensors with decoupled sensing mechanisms for detecting the target signal without being affected by the cross-sensitivity. Further, there is a need to develop an indigenous system which would not only monitor the vital signs but also takes an informed decision regarding the health of an individual. The issue can definitely be tackled by the use of decoupling mechanism and Machine/Deep learning wherein the sensor data can be trained for not only the classification of the sensor data but also for the early detection/diagnosis. Aims and methodology: 1. Fabrication of a functional nanomaterials based multifunctional physical sensors (breath, pressure and temperature) (Synthesis of materials at BITS and fabrication of device at RMIT) 2. Rigorous data collection of different breath patterns and VOCs, pulse rate and temperature variations (This would be performed at both BITS and RMIT) 3. Development of the versatile decoupling mechanisms and Machine/Deep Learning algorithm for accurate classification of the multiple stimuli sensor data (BITS) 4. Development of a frontend (dedicated android App) that collects accurate sensor data and transmits it to the smartphone (BITS). 4. Field testing of the fabricated prototypes and further collaborating with hospitals (BITS and RMIT).
BITS Supervisor
Dr. Parikshit Sahatiya
RMIT Supervisor
Prof. Madhu Bhaskaran
Required discipline background of candidate
| Discipline |
| Engineering, Engineering Physics |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Iron nanoparticles impregnated composite electrospun nanofibers for arsenic and microbes filtration from groundwater stream
Natural weathering and anthropogenic activities resulted in percolation of various contaminants and pathogenic bacteria in the groundwater, thereby declining its quality. Arsenic and microbes are two such lethal contaminants which causes varieties of diseases in human body, ranging from neural apathy to cancer. Amongst different removal strategies used, (i.e., adsorption, precipitation and coagulation) membrane filtration is attractive due to its high retention and flux. But membrane fibers prepared by conventional wet spinning method has higher pore sizes and faces selectivity issues, after few cycles of operation. This method also requires expensive spinneret assembly that require space and maintenance. Rather, electrospinning produces nanofibers with high porosity, specific surface area and controllable membrane thickness to directly promote infiltration rate and contaminant rejection ratio. Additionally, a specific ion can be removed by impregnating functional materials, like, nanoparticles in the polymer matrix. These fibers are known as composite nanofibers and they have both filtration and adsorptive properties. Current proposal aims to develop these composite electrospun nanofibers, by impregnating iron nanoparticles (IP) in different polymer melts, such as, dimethyl formamide (DMF) dissolved polyacrylonitrile (PAN), cellulose acetate (CA) and polyethersulfone (PES) on a polywoven ester fabric substrate. Electrospinning conditions, such as, applied electric field, distance between the needle and collector, melt flow rate, and needle diameter will be optimized based on the performance of the fibers, mainly in terms of their permeability, porosity, cut off, hydrophilicity, arsenic and microbial uptake capacity. Apart from that, these fibers will also be characterized based on their morphology and structure and mineralogical parameters. Best fiber with a specific preparation condition and composition will be chosen following this assessment. This fiber will be used for continuous filtration against arsenic and water borne pathogens as a function of different operating conditions, i.e., pH, pressure, flow rate and coexisting ions in crossflow and batch mode. Equilibrium uptake capacity of the best nanofibers will also be performed to know about its maximum uptake capacity for arsenic and microbes. As membrane fouling will be an inherent limitation in such operations, regeneration and disposal strategy of finally exhausted membrane will be designed.
BITS Supervisor
Dr. Somak Chatterjee
RMIT Supervisor
Namita Roy Choudhury
Other Supervisor BITS
Prof. Banasri Roy
Other Supervisor RMIT
Seungju Kim, Dr
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Environmental Science |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Assisted microwave annealing for spin defects in silicon carbide
Silicon carbide-based nanomaterials and thin films on insulators are relevant for biomedical imaging and quantum technologies applications due to their intrinsic high electrical and thermal conductivity, biocompatibility and fluorescent emission in the near-infrared. Current fabrication methods based on top-down approaches, such as chemical and mechanical ablation, ions implantation and conventional thermal annealing, are time-consuming, have a low yield and introduce surface defects that limit their application in quantum technology as the resulting material is not quantum grade. In this project, Molecular Dynamics simulations will initially be used to study the effect of assisted microwave annealing/fabrication in combination with ion implantation to enhance the yield of silicon carbide fluorescent spin qubits within nanomaterials and thin film on the insulator. The technique will then be experimentally tested, and the material properties will be characterised.
BITS Supervisor
Radha Raman Mishra
RMIT Supervisor
Stefania Castelletto
Required discipline background of candidate
| Discipline |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| Physics, Condensed Matter Physics |
|
Surfactant foams for the remediation of desert soil and soils in Australia
Stable surfactant foams are very effective in remediation of petroleum contaminated soils around the world but producing a highly stable surfactant foam remains the main barrier for remediation. In this project, stable surfactant foams will be generated with the aid of nanoparticles and will apply such foams in the remediation testing of petroleum contaminated desert soils in India and different soils in Australia. The soils involved in the work will be collected from field including actual petroleum industry contaminated sites and characterized in detail. Effect of shape, size and surface chemistry of the nanoparticles on the foam properties and the contaminated soil remediation will be studied. The work would include the use of nano-biochar, a promising material which, to date, has not been used in conjunction with surfactant foams. The stable foams produced will be also characterized with the help of Dynamic Foam Analyzer equipment available here in India. The optimization of the foaming behavior will be studied. Also it is proposed to perform the foam simulations to develop better understanding on the contaminated soil remediation mechanism.
BITS Supervisor
Pradipta Chattopadhyay
RMIT Supervisor
Dr. Jorge Paz-Ferreiro
Other Supervisor BITS
Prof. Banasri Roy
Required discipline background of candidate
| Discipline |
| Agriculture |
| Environmental Science |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Explainable Multimodal Emotion Recognition
This project aims to develop an explainable multimodal emotion recognition system that can accurately identify human emotions while providing interpretable explanations for its predictions. By integrating Large Language Models (LLMs) with explainability techniques, the system will offer insights into how different modalities, including text, audio, and facial expressions, contribute to emotion recognition.
The research will focus on building AI models that effectively fuses multiple modalities for improved emotion detection. LLMs will be leveraged to enhance the textual modality, improving the system’s understanding of linguistic cues related to emotions. To ensure the model’s decisions are trustworthy, the project will develop advanced explainability techniques. These methods will highlight the contributions of different input modalities, helping users understand the reasoning behind the system’s predictions. A significant aspect of this research is improving cross-modal interpretability. The project will investigate how LLMs can be used to generate human-understandable justifications for emotion predictions, ensuring that explanations align with human intuition. This may involve developing a hybrid approach that combines rule-based methods with deep/graph learning-based interpretability techniques, allowing for more coherent and contextually relevant explanations. To validate the effectiveness of the proposed system, extensive evaluations will be conducted.
BITS Supervisor
Dr. Aneesh Chivukula
RMIT Supervisor
Professor Feng Xia
Other Supervisor BITS
Professor Poonam Goyal
Other Supervisor RMIT
Professor Jenny Zhang
Required discipline background of candidate
| Discipline |
| Artificial Intelligence |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computer Science/Information Technology |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Neural Networks |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
Theoretical Techniques & Real-world Models for Safe & Trustworthy AI
We are witnessing a remarkable pace of progress in Artificial Intelligence (AI), including, more recently, with Large Language Models (LLMs). This pace of progress is widely expected to continue, fuelled by massive investments worldwide, and continues to create significant economic value. Some expect that these efforts will culminate in our ability to create Artificial General Intelligence (AGI). With the increasing deployment of these AI systems, where they complement or replace human decision-making, an important consideration is for these systems to be trustworthy. Informally, this would mean that their decisions are made by considering due merits of the case and not extraneous factors associated with prejudice. Similarly, with the development of AI models that have capabilities approaching that of humans, there is a desire to build safe models, i.e. models that will not act in ways that are detrimental to human interests. In both these cases, there is a need for techniques to audit trained models in order to determine and certify if they are trustworthy or safe. Currently, little is known about effective techniques to do this, and on theoretical limits on how well such techniques can work on contemporary AI models. The aim of this project is two-fold: (1) To apply techniques from Theoretical Computer Science to better understand limits on how well we can check trustworthiness and safety of arbitrary AI models. This is along the lines of some existing work by one of the senior supervisors (V. Ramaswamy). (2) To design new classes of AI models that are powerful, yet amenable to guarantees on trustworthiness and AI safety. To this end, we plan to leverage recent advances in Model Checking, Program Verification and Computational Logic, where one of the senior supervisors (J. Harland) has complementary expertise. We seek applicants with strong backgrounds/interests in Mathematics and/or Theoretical Computer Science, in addition to facility with programming. Knowledge of Deep Learning is a plus, but can also be picked up by motivated individuals early on in the program.
BITS Supervisor
Prof. Venkatakrishnan Ramaswamy, Assistant Professor
RMIT Supervisor
Prof. James Harland, Professor
Required discipline background of candidate
| Discipline |
| Data Science, Data Mining, Data Security & Data Engineering |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
|
Adversarial artificial intelligence on the Edge
Due to efficiency and latency issues, Machine Learning (ML) services using resources at the Internet-of-Things network edge near the data sources has emerged as edge intelligence (EI). EI is expected to push Deep Learning (DL) computations from the cloud to the edge thus enabling various distributed, low-latency, high-throughput and reliable ML services. The research challenges facing Edge DL for ubiquitous intelligence are training, inference, optimizing the ML on Edge. Suitable network architecture, hardware and software support are required for the DL computations in ML services. In this project, we will apply Adversarial Machine Learning (AML) to data streams collected for EI. Deep transfer learning strategies will be researched to facilitate AML on such resource-constrained edge devices. Storing, reusing and transferring information and knowledge from previous datasets and tasks has the potential to improve sample efficiency in AML. Domain adaptation is a research area in transfer learning that can model distributional shifts in data available for validating the robustness of AML algorithms. It will result in AML paradigms such as incremental learning, utility learning, reinforcement learning and online learning with class and cost distribution information for the transferable feature representations in data streams. Tensor decomposition is useful to analyze the transferable feature representations in such AML formulated as a non-linear optimization problem. The resultant optimization algorithms can be sped up with randomized algorithms that select columns according to a biased probability distribution for tensor decompositions. They can be interpreted as generalizations of low-rank tensor approximation methods representing statistically significant portions of the training data obtained from real world processes. We shall work on transfer metric learning to analyze the low-rank approximations of tensors in EI data streams with optimization methods such as canonical correlation maximization. They will be integrated with existing efforts for running DL on the edge such as Model Input narrowing down the ML searching space, Model Structure of specialized models that waive the generality of standard ML models in exchange for faster inference, Model Selection in the edge by combining different compression techniques in DL models balancing between performance and resource constraints.
BITS Supervisor
Dr. Aneesh Chivukula
RMIT Supervisor
Professor Jenny Zhang
Other Supervisor BITS
Dr Nikumani Choudhury
Required discipline background of candidate
| Discipline |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Networks and Communications, Wireless Comms, Telecommunications |
|
Advanced materials for clean energy and environment
This project aims to develop novel materials with distinct electrochemical properties and
Electrochemical energy storage (EES) systems are pivotal in transforming our lifestyle, as they are integrated into electronic components and electric vehicles (EVs). They also enhance the reliability of renewable energy production systems, such as fuel cells, solar cells, wind and tidal power, by providing a platform for large-scale energy storage. Among various EES systems, batteries and supercapacitors (SCs) are the primary systems capable of large-scale energy storage. However, they face challenges related to poor power and energy densities, respectively, which are primarily due to the limitations of the electrodes.
Furthermore, issues with the long-term stability of electrode materials can lead to rapid degradation of storage cells, necessitating replacement after a limited number of cycles. The limited lattice space in bulk electrode materials restricts ion insertion, resulting in slow charge-discharge rates, poor power density, and electrode failure. While energy density can be increased by maximising ionic storage, bulk materials only offer a finite number of intercalation sites, and their surface is not fully available for charge storage. Additionally, the reversible intercalation of ions leads to the expansion and contraction of electrode materials, causing mechanical stresses that can result in electrode cracking or delamination from the current collectors. Some materials also undergo phase transformations that produce redox-inactive phases, reducing capacity. These mechanical stresses and phase changes significantly impact the efficiency and lifecycle of EES systems. Therefore, to enhance the stability and cycle life of electrode materials, their phase transformation reactions should be perfectly reversible, and there should be sufficient space to accommodate the resulting stress, which is only possible with atomic-level reactions on planar surfaces.
Two-dimensional (2D) materials provide a promising platform for designing new electrode materials to overcome the limitations of various energy storage devices, particularly SCs and batteries. This project aims to develop heterostructures of these 2D materials with perfect face-to-face heterointerfaces at individual flakes. Both wet-chemical and physical methods will be employed to develop materials and explore their performance for different battery chemistries, such as sodium, potassium, zinc, and others.
BITS Supervisor
Sandip S. Deshmukh
RMIT Supervisor
Prof. Nasir Mahmood
Other Supervisor BITS
R. Parameshwaran
Other Supervisor RMIT
Muhammad Waqas Khan
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Materials Science |
| Mathematical Science |
| Mathematical Science |
|
Design of Low-Carbon Energy Systems towards Sustainable Cities
The rapid urbanization and industrial growth of cities have led to increased energy consumption, contributing significantly to carbon emissions and climate change. Designing low-carbon energy systems is critical for creating sustainable cities that minimize environmental impact while meeting the energy needs of a growing urban population. This project aims to develop innovative, efficient, and scalable low-carbon energy systems that can be integrated into urban infrastructures to promote sustainable urban development.
The following are the proposed objectives:
1. To design and develop low-carbon energy systems tailored for urban settings, focusing on renewable energy sources, energy storage, and energy efficiency.
2. To evaluate the environmental, economic, and social impacts of integrating low-carbon energy systems into existing urban infrastructures.
3. To create a roadmap for the implementation and scaling of low-carbon energy systems in cities, with specific attention to policy, regulation, and public engagement.
BITS Supervisor
Sandip S. Deshmukh
RMIT Supervisor
Arash Vahidnia
Required discipline background of candidate
| Discipline |
| Computer Science |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Environmental Science and Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
3D Printed Triply Periodic Minimal Surfaces (TPMS) Disc for Electric Vehicle's Brake Pad-Disc System
Wear is an undesirable material deterioration phenomenon that affects a wide range of technological systems, often leading to premature failures and causing health issues. In modern automotive technology, the sintered pad and disc system are the primary sources of non-exhaust pollution, releasing large amounts of wear debris or particulate matter during braking operations. Studies on these nano-sized airborne particles and their effects on human health have revealed that they are more hazardous to humans and the environment due to their increased surface area and higher reactivity.
Triply Periodic Minimal Surfaces (TPMS) are porous cellular-like structures that can be univocally defined by a set of trigonometric functions which, by definition, share the properties of a zero-mean curvature with a significantly increased surface area/volume ratio. These unique properties lead to promising results in structural and heat transfer enhancement.
Therefore, the project aims to develop an advanced tribologically optimized novel Triply Periodic Minimal Surfaces (TPMS) Fe-based disc structure for enhanced heat transfer during the braking process of automotive brake pad-disc system. This should support the wear reduction mechanism without compromising mechanical frictional performance, reducing brake dust load and extending service life.
To achieve this, the principal investigator will concentrate on the tribological pair/system of 1. Fe-based MMC powder comprises iron alloy, hard reinforcement phases, and friction modifiers for the brake friction material.
2. 3D printed TPMS counterpart disc with high wear resistance, strength, and lightweight properties.
Developing and investigating practical and cost-effective advanced tribological systems for brake pad-disc systems to reduce brake dust load and extend service life is highly desirable. The tribologically optimized friction material and TPMS disc are suitable for combustion engines and electric vehicles to meet low particulate matter emission requirements.
BITS Supervisor
Piyush Chandra Verma
RMIT Supervisor
Dr. Maciej Mazur Senior Lecturer
Other Supervisor BITS
Dr. Parikshit Sahatiya
Other Supervisor RMIT
Prof Raj Das
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Design, Design Engineering, Sustainable Design |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Engineering |
|
Diversity, Equity, and Inclusion (DEI) in Global Supply Chains
Current global crisis has forced supply chains to embrace diversity, equity, and inclusion (DEI) initiatives among suppliers, collaborators, and other stakeholders. Diversity encompasses various demographic, while equity is associated with ideas of fairness, and inclusion enhances the sense of belonging for individuals within a system. Supply chain DEI fosters variety of perspectives, thoughts, and solutions, that promotes innovation, creativity, and resilience in supply chains. Over time, supply chain with DEI practices have seen an increased probability. According to 2022 Gartner/ASCM Supply Chain DEI Survey, 75% of supply chain organizations concentrate on aspects related to diversity, while only 40% are actively engaged in specific Diversity, Equity, and Inclusion (DEI) projects or initiatives.
In India, uptake of DEI initiatives is ever more crucial as women are mostly limited to low-wage and low-skilled jobs. According to International Labour Organization (ILO), India's gender disparity has increased to 50.9%, with only 19.2% of the workforce are women. Better women participation could alone add $0.7 trillion to India’s GDP and reaching goal of $5 trillion economy by 2025. A recent Deloitte report, it was revealed that 70% of LGBTQIA employees experience workplace discrimination, a figure higher than the global average of 42%. Hence the aim is to investigate the DEI practices and develop a DEI index for Indian firms that supply products to the global firms such as Australian retailers.
This study will adopt a two-stage approach by employing qualitative and quantitative methodologies. Data will be collected from managers of Indian manufacturers and retailers of global firms sourcing from Indian manufacturers. In the first-stage, respondents from both retailers and manufacturers will be interviewed to identify the DEI practices and enablers to implement DEI practices in supply chains. Findings from the interview will be used to collect data for quantitative study. Fuzzy-set qualitative comparative analysis (fsQCA) approach is used to analyse quantitative data and develop a DEI index.
BITS Supervisor
Swati Alok
RMIT Supervisor
Dr. Aswini Yadlapalli
Required discipline background of candidate
| Discipline |
| Business |
| Completed Master degree (coursework/ thesis) in IT/ IS/ Business Management with CGPA at least 3.7/4 |
| MA in Development Studies |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
| MBA (Operations / Supply Chain and Logistics) |
|
Novel 2D Materials for photovoltaic and photocatalytic application
To meet the ever-growing demand for electrical energy, there is a need to harvest energy from sustainable sources, such as solar, thermal and wind. For these energy harvesting methods to succeed, materials with suitable properties and energy efficiencies are required. This project aims to investigate new materials for their potential energy applications. We will focus on 2D van der Waals materials, which can be used in low dimensional devices due to their size, flexibility, mechanical stability and unique material properties owing to their dimensionality. Various new 2D materials can be designed by functionalization as well as forming van der Waals heterostructures from the classes of existing 2D materials such as transition metal dichalcogenides, phosphorene, MXene etc. The materials that we will design and study in this project would be semiconducting in nature having a band gap within a specific range and band alignment suitable for photovoltaic and photocatalytic applications. First principles-based density functional theory (DFT) calculations and methods beyond DFT will be adopted for calculating the structural, electronic, optical and vibrational properties of the materials. The materials will be assessed for their suitability in photovoltaic and photocatalytic hydrogen production applications via water splitting and other chemical energy conversion reactions.
BITS Supervisor
Prof. Swastibrata Bhattacharyya
RMIT Supervisor
Prof. Michelle Spencer
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| Physics, Condensed Matter Physics |
|
AI-Driven Cross-Layer Security for Integrated Sensing and Communications in 6G Wireless Networks
Integrated sensing and communication (ISAC) is a transformative technology for 6G wireless networks, enabling the dual use of spectral resources for communication and sensing. This integration improves spectral efficiency, energy efficiency, and hardware utilization, addressing the demands of 6G applications like smart cities, autonomous transportation, and tactical networks. However, ISAC adoption faces challenges, including spectrum congestion, dynamic environmental changes, jamming and eavesdropping attacks, hardware limitations, and the need for real-time optimization. This research proposes a hybrid approach, combining model-based techniques for known or estimable parameters and AI/ML-driven methods for optimizing unnoticed anomalies.
i) At the physical (PHY) layer, model-based techniques will optimize known parameters, such as channel state information (CSI) and interference patterns, while AI/ML will detect and mitigate anomalies like jamming, eavesdropping, and environmental changes. Secure waveform and beamforming strategies will be designed for dual-functional radar-communication (DFRC) systems, ensuring high-performance communication and sensing under PHY-layer threats.
ii) At the medium access control (MAC) layer, AI/ML-enhanced protocols will optimize channel acquisition and resource allocation, dynamically adapting to jamming, eavesdropping, and network changes, while sensing-aided mechanisms will detect and mitigate MAC-layer attacks, such as denial-of-service (DoS) and spoofing.
Overall, the project will ensure end-to-end security by integrating PHY and MAC-layer solutions, using AI/ML to optimize cross-layer performance metrics like throughput, latency, and detection accuracy under adversarial conditions. Insights from this research will pave the way for ISAC-driven advancements in emerging technologies, such as meta-material-based intelligent surfaces and photonics-based sensors.
BITS Supervisor
Sandeep Joshi, Assistant Professor
RMIT Supervisor
Saman Atapattu, ARC Future Fellow (Senior Research Fellow)
Required discipline background of candidate
| Discipline |
| Information and Communications Technology |
| Networks and Communications, Wireless Comms, Telecommunications |
| Robotics, Sensors, Signal Processing, Control Engineering |
| Sound knowledge in mathematics |
|
AIE-carbon dots-based microfluidic biosensing platforms for enzymatic biomarker detection in early disease diagnosis
Early detection of disease-specific biomarkers is essential for timely diagnosis and treatment. Enzymatic biomarkers provide crucial insights into pathological conditions at their initial stages. For instance, nitroreductase is associated with cancer progression, ß-galactosidase in urine serves as an early indicator of diabetic kidney disease, and carboxylesterase is a biomarker for hepatocellular carcinoma. However, current detection methods often lack the required sensitivity, selectivity, and practicality, emphasizing the need for reliable diagnostic platforms.
This project proposes fluorescence-based microfluidic sensing platforms integrating advanced nanomaterials for improved biomarker detection. Red-emitting carbon dots (RCDs) offer superior sensitivity and biocompatibility compared to conventional probes. While blue- and green-emitting carbon dots are well studied, red-emitting variants with aggregation-induced emission (AIE) remain largely unexplored. Additionally, CoOOH nanoflakes act as nanoenzymes with oxidase-like activity, enabling efficient fluorescence quenching for highly selective biomarker detection.
Integrating these nanomaterials into microfluidic analytical devices ensures precise reaction control, minimal sample volumes, and high-throughput analysis. This project aims to develop and validate a fluorescence-based microfluidic system for real-time biomarker detection, enhancing diagnostic accessibility.
ObjectiveDevelop red-emissive AIE carbon dots using eco-friendly methods.Create a CoOOH-based sensory platform for detecting nitroreductase, ß-galactosidase, and esterase.Design microfluidic solutions for precise enzyme detection. Methodology Synthesis & Characterization of AIE CDs. CoOOH nanoflakes will be synthesized. Analyte-specific synthesis of pseudoprobes. Evaluation & Validation: Optimization studies will be conducted with different parameters. UV-Vis and fluorimetric study to assess enzyme interactions, selectivity and LOD studies Microfluidic Device Development: CAD modeling using SOLIDWORKS will guide device design, followed by PDMS injection molding at the MNRF PDMS Laboratory (RMIT University). Validation will include optical microscopy for structural integrity and fluorescence microscopy for biomarker interaction analysis. By integrating AIE-active carbon dots with microfluidic biosensing, this project aims to enable early disease detection, improving patient outcomes.
BITS Supervisor
AMRITA CHATTERJEE
RMIT Supervisor
Cesar Sanchez Huertas
Other Supervisor BITS
Sanket Goel
Other Supervisor RMIT
Francisco Tovar Lopez
Required discipline background of candidate
| Discipline |
| Chemistry |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Development of nano-myco-membrane based integrated prototype for the treatment of real-time textile effluents
Summary: Textile industries are the 3rd largest user of freshwater resources in the world, employing water in processes such as bleaching, scouring, dyeing, and finishing. The textile industries in Rajasthan, India, significantly contribute to social and economic empowerment. However, the majority of these industries discharge their effluents directly into the environment without any treatment. The important pollutants present in these effluents are chemical dyes and toxic heavy metals. Prof. Gupta’s research group at BITS Pilani has reported the synthesis and potential application of various eco-friendly nano-adsorbents, including functionalized Cu-based metal oxide nanoparticles, metal oxide frameworks (Ca-MOF, Fe/Al MOF and their GO composites) and composites (silver-yttrium oxide nanocomposites), for the removal of heavy metals and dyes from synthetic wastewater. Prof. Panwar’s research group at BITS Pilani has identified fungal isolates (Aspergillus terreus SJP02 and Ectophoma multirostrata SJP03) for the efficient removal of heavy metals and dyes from synthetic wastewater. Dr. Pramanik’s research group at RMIT, Australia, specializes in the development of separation-based technology for the removal and recovery of heavy metals from wastewater. Given the complexity of pollutants and the substantial volume of effluents, our proposed research aims to develop a nano-myco-membrane-based integrated prototype specifically designed for treating real-time textile effluents. This innovative approach not only seeks to address the removal of pollutants but also focuses on the recovery of heavy metals, offering an eco-friendly and cost-effective solution to a pressing environmental challenge.
Aim: The proposed research work aims to develop a nano-myco-membrane based integrated prototype for the treatment of real-time textile effluents and recovery of heavy metals.
Methodology:
• Collection of wastewater samples from various textile industries of Rajasthan, India and their compositional characterization.
• Fabrication of a range of nano-composite membranes with tuneable pore size and high water permeance for the removal of dyes and heavy metals and elucidate the associated removal mechanisms i.e., sieving, electrostatic interaction and/or Donnan effect, thus allowing removal optimization.
• Investigate the effect of various physiochemical characteristics of the nanocomposite membrane and selected pollutants to investigate the factors that govern perform.
BITS Supervisor
Prof Suresh Gupta
RMIT Supervisor
Dr Biplob Pramanik
Other Supervisor BITS
Jitendra Panwar
Other Supervisor RMIT
Prof Jega Jegatheesan
Required discipline background of candidate
| Discipline |
| Chemical Engineering |
| Chemistry or Chemical Sciences |
| Environmental Engineering |
| Materials Science |
|
Development of a Fuel Cell – Battery Hybrid Energy System for High Endurance Drone Application
Recently drones are gaining popularity for variety of applications viz. military, agriculture, inspection and monitoring etc. Traditionally, IC engines are used to power drones however, they emit greenhouse gases, have vibration, exhibit acoustic and thermal signatures. Electric-power systems such as battery, fuel cell etc. can eliminate these issues. Battery based propulsion systems are quite popular however, they have very less energy density (250 Wh/kg) and less endurance (30 min). Fuel cells are light weight and have high energy density (1000 Wh/kg) and therefore can improve the endurance of drones manyfold. However, fuel cells have low power density and therefore they alone are not sufficient to power the drones during high power requirements. Instead of stand-alone battery or fuel cell, a hybrid energy system can be more effective in powering drones. Therefore, this study aims to develop a fuel cell-battery hybrid energy system for high endurance drone application. The specific objectives are:
1. Development of a fuel cell – battery hybrid energy system.
2. Development of an energy management system (EMS) for optimal control of power splitting between fuel cell and battery.
3. Testing and performance assessment of the hybrid energy system under different operating conditions.
4. Incorporation of the hybrid energy system into drone platform and preliminary flight tests.
The proposed hybrid system consists of a fuel cell and a battery connected in parallel. It will be integrated with a DC-bus, by suitable power electronic converters. An EMS will optimize the power split between fuel cell and battery. The scheduling of prioritizing the energy sources will be decided based on the energy management algorithm. The algorithm will be embedded on the low cost Raspberry Pi processor. The associated sensor (voltage, current, temperature) data will be processed by the algorithm and thus enabling the control switches for real time operations. The brushless DC (BLDC) motor will be controlled by the motor controller powered by the DC bus. The BLDC motor will run the propeller. The fuel cell and battery are very sensitive to the operating conditions therefore, the hybrid energy system will be tested at different conditions by placing them in an environmental chamber. The hybrid energy system will be installed onto the drone platform. Initial tests will be conducted to check functionality, endurance, range etc.
BITS Supervisor
Naveen Kumar Shrivastava
RMIT Supervisor
Arash Vahidnia
Other Supervisor BITS
Dr. Ankur Bhattacharjee
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
AI/ML-based Techniques to Enhance Grid Integration of Renewable Energy and Electric Vehicles
The operational aspects of future power systems are expected to be influenced significantly by the increasing grid integration of renewable energy and electric vehicles (EVs). This PhD project will attempt to develop AI-based tools and techniques for increasing the penetration of renewable energy and EVs on future power systems and will investigate the enabling technologies to facilitate high EV integration into the electricity grids. This project aims to explore the following research contents:
• Development of AI/ML-based models for spatiotemporal renewable generation and EV charging load at the distribution substation based on data-driven approaches.
• Articulation of an appropriate simulation model of a distribution network considering correlations among EV, solar PV, and system loads.
• Detailed time-sequential simulation studies with collected historical data on the renewable and EV grid impact assessment.
• Identification and validation of the AI/ML-based mitigation techniques for EV grid integration problems; and
• Provision of recommendations on the planning and operational strategies of the renewable and EV-rich distribution networks.
To achieve the outcomes as per the abovementioned objectives, the following methodology will be followed:
• Collecting historical renewable generation and EV charging data from a wide range of customers over the entire annual cycle
• Developing spatiotemporal renewable generation and EV charging profiles in a representative distribution network
• Performing power system simulation with the spatiotemporal renewable generation and EV data in a combined MATLAB-DIgSILENT power factory software package
• Identifying distribution grid problems, including voltage violation, line overloading, and substation capacity limit violation
• Advanced AI-driven techniques, such as deep learning, hybrid deep learning, and transfer learning will be implemented to ensure accuracy and efficiency.
• Validating the proposed solution approaches considering representative network operational scenarios
• The solution platform will go through rigorous testing and experimentation both in the software platform and in hardware-in-the-loop (HIL) loop facilities
• System stability with the new types of tools and resources (such as demand-side management, electric vehicles, and virtual power plants), and grid-forming (GFM) technologies will be assessed and ensured.
BITS Supervisor
Dr. Alivelu Manga Parimi
RMIT Supervisor
Dr. Kazi Hasan
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computer Science/Information Technology |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
|
DEVELOPMENT OF A DIGITAL TWIN MODEL FOR ASPHALT PAVEMENT STRUCTURES
Summary :
Over the past 50 years, the UAE has witnessed a significant transformation in its road network, providing citizens with well-paved highways and flyovers. However, escalating traffic demand, construction projects, and rising temperatures pose challenges, particularly road pavements. The expected temperature increase can impact pavement structural performance of asphalt pavements, which make up for more than 90% of the roads in the UAE. To address this, continuous monitoring is essential, moving from traditional periodic inspections to intelligent remote monitoring using IoT and embedded sensing technologies. A Digital Twin Model (DTM) is crucial, synchronizing real-time data from sensors to create a virtual representation of the pavement structure. This approach, gaining popularity across various infrastructure sectors, enables dynamic updates for timely maintenance decisions. A Digital Twin Model (DTM), as demonstrated for an asphalt pavement in Ireland, is essential, synchronizing real-time data from sensors to create a virtual representation of the pavement structure. The primary objective of this project is to develop a 3D digital twin model of asphalt pavement structure, to monitor the structural changes under real-time loading and environmental conditions. This can be achieved through the following research objectives.
Objectives :
1) Develop a DTM using a 3D Finite Element Method (FEM) based model to monitor the critical pavement responses
2) Develop machine-learning techniques to predict the heat distribution in pavement layers from weather data and temperature probes
3) Embed temperature and strain sensors at various depths of pavement layers
4) Establish the physical-to-virtual connection to update the DTM model parameters
5) Update the structural reliability, and propose the optimal timings for pavement maintenance
Methodology :
The development of the DTM to monitor the structural responses of the pavement is carried out in two phases in this project. Phase 1: a thermal digital twin model is developed to predict the predict heat distribution in the pavement layers.
Phase 2: the predicted temperature distribution will be used as input, along with the field strain measurements, to build the 3D FEM model.
Steps :
1) Get telemetry data from the physical road structure
2) Detect and diagnose
3) Develop real-time FEM-based model
4) Model Calibration
5)Result Collection
6)Decision support based on AI algorithm
BITS Supervisor
Deepthi Mary Dilip
RMIT Supervisor
Mojtaba Mahmoodian Dr
Other Supervisor RMIT
Dr. Amir Sidiq
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
|
Climate-Resilient Smart Groundwater Recharge Solutions for Arid and Semi-Arid Areas
Aims: Groundwater levels over much of India and some regions of Australia are declining because usage exceeds seasonal monsoonal recharge. This proposal aims to increase groundwater recharge through groundwater recharge potential zones (GRPZ) using remote sensing and geospatial technology to target areas of more efficient infiltration for installing rainwater harvesting (RWH) infrastructure. Machine learning algorithms will be used to map GRPZ. Groundwater level changes will be compared with AI/GCM climate projections to gauge the effectiveness of increased recharge in mitigating climate change impacts. Water samples from rainwater and groundwater will be analyzed for quality. Groundwater users in the target areas will be surveyed to design an incentivization and capacity-building program to encourage the adoption of improved infiltration technology across both countries.
Objectives:
1. increasing RWH efficiency through i. better siting of infrastructures using remote sensing and geospatial technology, ii. creating an AI system to GRPZ.
2. to evaluate RWH groundwater resiliency and how it can offset regional climate change,
3. developing an incentive plan as well as a capacity building and training plan for groundwater stakeholders to overcome impediments to widespread adoption of the technology.
Methodology
Phase I: Improving efficiency of RWH through targeting areas that allow maximum infiltration. Activities include:
1. Rural area will be chosen to identify the parts with porous soil
2. GRPZ mapping using machine learning and remotely sensed and geospatial datasets.
3. Monitoring bores with water level loggers will be installed to record the impact of more efficient RWH on the local groundwater levels.
4. RWH sites will be located to minimise the potential for contamination by surface pollutants.
Phase II: Developing AI framework to analyze the relationship between climate change and groundwater levels at a regional level. Steps include:
1. Integration of Data Sources in a unified platform
2. Machine Learning/Deep Learning (EfficeintNet, ResNet, MobileNet, Vision Transformer, etc.) Pipeline
Phase III: Widespread adoption of the proposed RWH technology. Steps include:
1. Identify and map key stakeholders
2. Statistical and econometric analysis
3. Develop a Computable General Equilibrium (CGE) model
4. Engage with local communities through surveys, interviews, and focus group discussions.
BITS Supervisor
Dr. Rallapalli Srinivas
RMIT Supervisor
Prof. Guomin (Kevin) Zhang
Other Supervisor BITS
Prof. Ajit Pratap Singh
Other Supervisor RMIT
Muhammed Bhuiyan Senior Lecturer
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Civil Engineering, Structural Engineering |
| Environmental Engineering |
| Natural Resources, Water Resources |
|
Environmental, social, and governance (ESG) practices and firm performance in India: The role of board gender diversity and ownership structure
This study delves into the complex interrelationships among environmental, social, and governance (ESG) practices, board diversity, ownership structure, and firm performance within the Indian business landscape. By analyzing financial reports spanning from 2010 to 2023, the research aims to uncover the implications, benefits, and challenges associated with integrating ESG considerations into business operations using robust panel data econometric models to control for industry and time effects as well as the potential endogeneity issues.
This research will employ quantitative methods, including GLS regression, propensity score matching estimates, instrumental variable analysis, differences-in-difference, and system GMM, to estimate and analyze data extracted and manually collected from secondary sources.
Moreover, it emphasizes the necessity of a comprehensive approach to corporate sustainability. As businesses increasingly recognize the importance of sustainable practices, this study provides valuable insights for policymakers, corporate leaders, and scholars. Furthermore, the research examines the influence of board gender diversity and ownership structure on the relationship between ESG practices and firm performance. It investigates how the gender composition of the board and ownership attributes shape overall firm performance dynamics.
Specifically, the study explores the impacts of regulatory measures such as the Companies Act (2013) on board gender diversity and ownership structure and their subsequent effects on firm performance. Additionally, it assesses whether these measures contribute to sustainable growth and improved social practices, considering the different perspectives on corporate.
This research project is suitable for candidates with expertise in econometrics, programming (R, Stata), and corporate finance literature.
BITS Supervisor
Prof. R. L. MANOGNA
RMIT Supervisor
Dr. Md Safiullah
Required discipline background of candidate
| Discipline |
| Banking, Finance and Economics |
| Business |
|
Adversarial deep learning in next best action marketing
Recommendation systems identify a fraction of items from a very large inventory of items and recommend them to a user. They are trained with machine learning algorithms to maximize a user-centered utility or a business process-oriented one. Automated next-best action recommendation for each user in a sequential, dynamic and interactive context has been widely needed in natural, social and business decision-making.
Personalized next-best action recommendation must involve multi-sequence interactions between states, behaviors and actions, and their reactions to their counterpart's actions. No existing modeling theories and tools, including Markovian decision processes, user and behavior modeling, deep sequential modeling, and personalized sequential recommendation, can quantify such complex decision-making on a personal level.
In this project, we will take a data-driven approach to learn the next-best actions for personalized decision-making with deep learning. We will develop a recommendation system for marketing strategy predictions. We will focus on fully data-driven learning methods for generating recommendation data such as Collaborative Filtering (CF) and their state-of-the-art variants in deep learning such as Factorization machines (FMs) and Graph Neural Networks (GNNs). The data representation from raw data will be done in the extract-transform-load (ETL) process for data integration, cleaning, transformation, visualization, smoothing, and reduction. It will be extended with steps for data governance on the datasets procured from real-world application. Then the plan is to build more complex models having improvements like link prediction and graph pattern mining to CF algorithms. We will then collect user feedback and incorporate into the data analytics project lifecycles. CF is a popular technique for estimating preference of end users by discovering the implicit correlation between the revealed responses of users. Back-end data architectures will be proposed to create efficient data pipelines. Our research efforts will be directed towards improving the interpretability of the deep learning to give personalized recommendations to individual users. Observations that contradict existing classifications may point to emerging topics. Making the wrong choices can be expensive. So we want to build deep learning models to predict the best offerings to each user, but with the least cost.
BITS Supervisor
Dr. Aneesh Chivukula
RMIT Supervisor
Dr. Ashish Kumar
Other Supervisor BITS
Dr. Manish Kumar
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Business Analytics |
| Data Science, Data Mining, Data Security & Data Engineering |
| Neural Networks |
|
Optimizing Systems for Edge-Based Machine Learning Models
Edge-based machine learning (ML) models are essential for real-time data processing and decision-making in drones, self-driving cars, and healthcare. Unlike traditional centralized ML models, these models operate in a distributed manner, processing data across heterogeneous edge devices (smartphones or single-board computers) and networks (wireless or wired or bluetooth), posing challenges regarding data privacy, system heterogeneity, and scalability.
This project proposes a novel framework to address these challenges, enabling efficient deployment of distributed ML models on edge devices, including data privacy-aware federated learning (FL) models. The framework will incorporate edge devices, models, and datasets' heterogeneous nature while ensuring data privacy and providing a plug-and-play approach for non-technical users. The optimizations intended in the framework will also contribute to energy usage minimization so that battery-operated edge devices can be used optimally.
The key objectives are: (1) Develop a framework that integrates distributed ML and FL models, accounting for device heterogeneity and data privacy; (2) Evaluate the framework's performance on diverse use cases and experimental testbeds; (3) Derive a mathematical model to characterize the relationship between edge device parameters, ML models, and datasets.
The methodology involves: (1) Conducting a comprehensive literature review of state-of-the-art distributed ML and FL techniques; (2) Deploying a testbed to run experiments with diverse datasets, collecting time-series data on system usage and model performance; (3) Formulating a mathematical model based on the collected data; (4) Developing the proposed framework; (5) Testing the framework on real-world use cases in healthcare and drone applications.
This research will contribute to the advancement of edge computing by providing a framework that enables efficient deployment of distributed ML models on heterogeneous edge devices while ensuring data privacy and scalability, ultimately enhancing real-time decision-making capabilities in critical domains.
BITS Supervisor
Arnab K. Paul
RMIT Supervisor
Malka N. Halgamuge
Other Supervisor RMIT
Prof Afreen Huq
Required discipline background of candidate
| Discipline |
| Computer Science and Engineering/Computer Engineering |
| Computing: Collaborative and Social Computing, Computing Education, Computer Systems,Human Computer Interaction |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Information and Communications Technology |
|
Unravelling the effects of tool and workpiece interactions on functional surface generation in micromachining of additively manufactured difficult-to-cut alloys
The recent technological shifts have led to a tremendous rise in the miniaturized devices, components, features and functional surfaces which find their applications in space, optics, electronics, defense, medical and automotive industries. Various micro-manufacturing techniques generate micron-sized features on substrate materials or produce functional surfaces. Mechanical micromachining offers high precision, flexibility in the choice of work-piece materials, and high efficiency, which are attributable to low cycle time and ease of material removal. Several studies have been carried out in the mechanical micromachining of conventional engineering materials; however, the studies, including numerical and experimental investigations on additively manufactured difficult-to-cut materials, are limited.
Additively manufactured difficult-to-cut alloys tend to cause challenges in machining due to continuous tool wear, irregular chip formation and deterioration in surface quality.
Owing to continuous involvement between the cutting tool and the workpiece materials during the machining of microfeatures, the cutting edge is subjected to high stresses and consequent tool wear while machining high-strength materials. As the tool wear increases, the material removal mechanisms also tend to change, consequently affecting surface integrity. The surface may get affected in the form of defects such as micron-size burrs, chattering marks and tool marks. The proposed work suggests the modelling-based approach to predict tool wear mechanisms, material removal mechanisms and the effects of cutting forces and vibrations on the quality of the generated surface. Numerical modelling based on additively manufactured material parameters is proposed to simulate the micromachining process for cutting forces. The preliminary experiments will be carried out to validate the simulated results. The functional surface desired to perform a specific function (wettability or tribology-related) will be fabricated using mechanical micromachining. Post fabrication, surface quality will be thoroughly investigated regarding the machined features' size, surface finish, and subsurface damage.
BITS Supervisor
ANUJ SHARMA
RMIT Supervisor
Songlin Ding, Professor
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| ME (Industrial/Production Engineering) |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Membrane degradation and its mitigation strategies in low-temperature proton exchange membrane (PEM) fuel cells for heavy-duty electric vehicles
Proton exchange membrane (PEM) fuel cells are used in fuel cell electric vehicles due to key benefits such as fast startup and quick response to dynamic loads. However, despite significant advancements in recent years to improve their durability, PEM fuel cells still fall short of internal combustion engines in terms of lifespan. Various degradation mechanisms impact different components of PEM fuel cell stacks, with the membrane being particularly susceptible to deterioration.
The load profile of PEM fuel cells plays a crucial role in membrane degradation, especially in automotive applications, where frequent acceleration, deceleration, startups, and exposure to diverse climatic conditions accelerate both mechanical and chemical wear.
This project aims to investigate membrane degradation behavior in automotive applications, identifying the underlying mechanisms and influencing factors. The insights gained will inform the development of effective mitigation strategies and implementation methods to extend the lifespan of PEM fuel cells. While the primary focus is on heavy-duty vehicle applications—considered an early adopter of fuel cell technology—the findings and methodologies are expected to benefit a broad range of automotive and mobile applications, including passenger cars, off-road machinery, trains, and maritime transport.
Keywords: Hydrogen mobility, PEM Fuel Cell, Advanced materials, PEM fuel cell durability, Membrane degradation
BITS Supervisor
Prof. Jay Pandey
RMIT Supervisor
Bahman Shabani, PhD
Other Supervisor BITS
Mohit Garg
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Engineering, Engineering Physics |
|
Real time measurement of moisture using a quartz crystal resonator operating at a constant frequency and amplitude
Summary: Moisture sensors have applications in various sectors including agriculture, automobiles, food processing industry, medical equipment, pharmaceutical and waste water treatment plants, to name but a few. Traditional moisture content estimation includes thermogravimetric analysis and multi-spectral remote sensing-based approaches relying on absorptive properties of water in near-infrared or shortwave-infrared wavelengths. However, the conventional moisture measurement methods involve cumbersome steps and lack sensitivity. Hence, there is an unmet need to come up with a simple and sensitive tool for real time quantification of moisture.
Aims:
1. Investigation of suitable coatings on sensor surfaces for more moisture adsorption sites
2. Development of cost-effective and scalable sensor for rapid and real time monitoring of moisture
3. Comparison of the developed moisture sensor with the state-of-the-art techniques
Methodology: Quartz crystal resonator (QCR) is entirely electronic and simple in configuration and has therefore gained wide attention as a rapid and on-line detection sensor in both liquid and gaseous mediums [1]. Adoption of fixed frequency drive (FFD) method in conjunction with microfluidics and a temperature controlled QCR will be an exemplary application for real-time monitoring of moisture. In FFD method, a QCR is driven continuously at a fixed frequency and amplitude and the response is analytically interpreted to obtain resonance frequency and dissipation shifts employing imaginary and real components of experimentally recorded electrical impedance respectively. FFD technique will be applied to detect moisture employing coated QCRs which are obtained using either drop casting, spin coating or spray coating techniques. Various coatings including graphene oxide and indium oxide quantum dots, to name but a few will be explored for the project. The interaction between coating modified QCR surface and moisture will be quantified in terms of QCR resonance frequency and dissipation (acoustic energy loss) shifts with respect to baseline signal devoid of moisture. Initial experiments will be carried out using 14.3 MHz QCRs. QCRs with higher fundamental frequencies ranging from 50 to 250 MHz will be explored for sensitive detection of moisture.
Reference
[1] A. Alassi, M. Benammar, and D. Brett, “Quartz crystal microbalance electronic interfacing systems: A review,” Sensors (Switzerland), vol. 17, no. 12, pp. 1–41, 2017, doi: 10.3390/s1712
BITS Supervisor
Dr Arnab Guha, Assistant Professor
RMIT Supervisor
Dr Henin Zhang, Senior Lecturer
Other Supervisor BITS
Satish Kumar Dubey
Other Supervisor RMIT
Amirali Khodadadian Gostar
Required discipline background of candidate
| Discipline |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
Adoption of Cloud Computing by Indian Manufacturing MSMEs
In India, the Manufacturing Micro, Small, and Medium Enterprises (MSMEs) sector, often called the backbone of the economy, is gradually embracing cloud technologies to enhance agility, streamline processes, and drive innovation. This sector comprises 36 million units, provides job opportunities to over 80 million people, and contributes around 8.0% to GDP and 40.0% to exports.
The broad definition of MSME classification was first defined in 2006 by the MSMED Act 2006 and further modified after the Gazette of India notification dated 01.06.2020. This notification is classified based on annual turnover and Investment in Plants and Machinery. According to the above notification, if the maximum investment in Plant and Machinery is INR 10 million or the turnover is INR 50 million, it is termed a Micro Industry. If the maximum investment in Plant and Machinery is INR 100 million or the turnover is INR 500 million, it is termed a Small Industry. If the maximum investment in Plant and Machinery is INR 500 million or the turnover is INR 2500 million, it is termed a Medium Industry.
Cloud computing refers to a technology based on the Internet through which information is stored in servers and provided Software as a Service (SaaS) on request to the customers. MSMEs need to adopt innovations in ICT, especially Cloud Computing (CC) applications, to cut down the enterprise's costs and efficiently function in the highly competitive global environment. It is worth mentioning that cost-effective technologies are now available in the ICT domain for the MSMEs. It may be noted that no upfront investments are needed to use CC applications as they are available at relatively cheap rates and are easy to adopt. The government of India has proposed a subsidy of up to 1 Lakh rupees for MSMEs to encourage them to adopt CC applications. It has been observed that, generally, Indian MSMEs are not utilizing the CC applications to promote their business activities and not availing their benefits, mainly due to lack of awareness, lack of trust, and financial issues.
This research proposes identifying the drivers and barriers to cloud computing adoption in the context of Indian Manufacturing MSMEs through an extensive literature review and panel experts. Then, MSMEs will be surveyed to test the impact of these factors on cloud computing adoption.
Findings will be published and shared with policymakers in India. Also, a framework will be suggested for adopting CC by Indian MSMEs.
BITS Supervisor
RAJESH MATAI
RMIT Supervisor
Siddhi Pittayachawan
Required discipline background of candidate
| Discipline |
| Computer Science and Information Systems |
| Computing: Collaborative and Social Computing, Computing Education, Computer Systems,Human Computer Interaction |
| Information and Communications Technology |
| Information Technology |
| MBA (Operations / Supply Chain and Logistics) |
| ME (Industrial/Production Engineering) |
|
Redefining Business Security in the Digital Age: Blockchain and Quantum Resistance Strategies
The digital age has brought unprecedented business opportunities but has also introduced new security challenges. This project aims to address the threats posed by the arrival of quantum computing to traditional encryption methods and explore the potential of blockchain technology to provide a secure and tamper-proof solution.
The primary objectives of this project are twofold. First, it seeks to investigate the vulnerabilities of existing cryptographic systems to quantum computing attacks and evaluate the readiness of businesses to adopt post-quantum cryptography. Second, it aims to explore integrating quantum-resistant cryptographic methods, such as lattice-based and hash-based signatures, into blockchain platforms.
The methodology will involve a comprehensive literature review to understand the state-of-the-art in quantum computing, blockchain technology, and post-quantum cryptography. Computational resources will be allocated to run simulations and benchmarking tests on various cryptographic algorithms and blockchain implementations. Additionally, test networks will be established to evaluate the performance and security of quantum-safe blockchain platforms.
Through this project, we aim to raise awareness among businesses and organisations about the potential risks posed by quantum computing to their data security and the need to adopt quantum-resistant strategies. Furthermore, a framework will be developed to assess organisations' readiness for post-quantum cryptography and provide recommendations for implementing quantum-resistant blockchains.
By redefining business security in the digital age, this project will contribute to developing robust and future-proof solutions, ensuring the protection of sensitive data, and promoting trust in digital transactions. The findings and recommendations will be disseminated through top-tier academic publications, industry workshops, and outreach activities, empowering businesses to navigate the challenges of the quantum era.
BITS Supervisor
Dr Nikumani Choudhury
RMIT Supervisor
Malka N. Halgamuge
Other Supervisor BITS
Prof. Barsha Mitra
Other Supervisor RMIT
Dr Ancy Gamage
Required discipline background of candidate
| Discipline |
| Computer Science and Engineering/Computer Engineering |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Engineering, Engineering Physics |
|
Advanced Graphene Nanocomposites for Ambient Energy Harvesting in IoT Applications
Fabrication of Graphene-Based Polymer Nanocomposites
Graphene-based polymer nanocomposites can be synthesized using solvent processing, in-situ polymerization, and melt blending. Polymers, as flexible thermoelectric (TE) materials, offer low thermal conductivity and mechanical flexibility. However, their inherently low electrical conductivity can be enhanced by incorporating graphene derivatives into conjugated polymer composites. In this study, ultrasonic and molding techniques will be employed to fabricate PVA-based nanocomposite TE films.
Material Characterization and Performance Evaluation
The fabricated nanocomposites will be characterized through various tests, including thickness and mass measurement, hardness testing, thermal and oxidative stability analysis, and product lifetime assessment. Moisture and volatile components will be analyzed using a Thermogravimetric Analyzer (TGA). The electrical properties of thin films will be evaluated by measuring sheet resistance with a four-point probe system. The Seebeck coefficient will be determined using a four-probe setup integrated with two T-type thermocouples, two copper wires, a Keithley 2000 multimeter, a temperature controller, and data acquisition software. Additionally, electronic carrier concentration and mobility will be assessed following the ASTM F76-08 standard using a van der Pauw geometry setup. An optimization study will be conducted to determine the optimal graphene nanofiller concentration within the polymer matrix.
Numerical Simulation Study
This study also includes a numerical simulation of the thermoelectric behavior of the system using COMSOL Multiphysics. The model will analyze the effects of parameters such as temperature and bending stress to optimize thermoelectric performance and enhance TE efficiency.
Machine Learning Optimization
Machine learning techniques will be applied to optimize both the material properties and thermoelectric device characteristics, ensuring improved performance and efficiency.
BITS Supervisor
Dr Ravindra G Bhardwaj
RMIT Supervisor
Prof. Xu Wang
Other Supervisor BITS
Harpreet Singh Bedi
Other Supervisor RMIT
Professor Sumeet Walia
Required discipline background of candidate
| Discipline |
| Materials Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
DESIGN AND DEVELOPMENT OF METASURFACE BASED OPTICAL RECTENNA FOR SOLAR ENERGY HARVESTING APPLICATIONS
Solar energy harvesting is the process of extracting the power from solar energy (sunlight) and converting it into DC power and using this power to drive electrical devices. As the technology is evolving towards 6G and the number of electric-based devices is increasing every year, solar energy scavenging is bound to become an alternative means for powering the devices by utilizing the solar energy from the surrounding environment. Major applications of this technology are the replacement of batteries, powering sensors in challenging environments, etc. Solar energy scavenging is accomplished using special devices known as Optical rectennas. which consists of the antenna-coupled diode (a rectifying network) operating at optical frequencies.
Optical rectennas are devices designed to convert high-frequency electromagnetic waves, particularly in the terahertz range, into direct current (DC) electricity. This technology holds potential for various applications, including solar energy conversion. Optical rectennas can potentially achieve higher efficiency in converting certain wavelengths of electromagnetic radiation into electricity compared to traditional solar panels. An optical rectenna incorporates a submicron antenna and an ultra-high-speed diode. The optical rectenna absorbs electromagnetic radiation and converts it to current. A diode rectifies the AC, providing DC electrical power. Compared to conventional solar cells, which absorb photons and generate electron-hole pairs to provide electrical power, rectennas seem to rely on a classical electromagnetic wave view of light. Optical rectennas may require fewer materials compared to traditional solar panels, which often use semiconductor materials like silicon. This could lead to cost savings and a smaller environmental footprint.
BITS Supervisor
Runa Kumari
RMIT Supervisor
Stefania Castelletto
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
|
Metal-Organic Frameworks-MXene based composites: Nanoarchitectonics for developing advanced electrode for Zn-batteries
To address today’s energy crisis with a sustainable solution, Zn metal batteries show promise for large-scale energy storage due to their inherent safety, eco-friendliness, and affordability. However, challenges such as hydrogen evolution, Zn corrosion, and dendrite growth hinder their practical use. To address these issues, researchers are tasked with developing functional materials to improve the specific capacity and cyclic stability of Zn-air/ion batteries.
Metal–organic frameworks (MOFs) have emerged as promising materials for energy applications thanks to their high surface area, porous structure, and customizability. However, pristine MOFs often suffer from low electronic conductivity and chemical instability, limiting their large-scale use. On the other hand, MXene, with abundant surface terminations and high metallic conductivity, can be a good substrate or filler material for MOFs to improve their stability and conductivity compared to their pristine counterparts. This project aims to ameliorate the electrochemical properties of diverse tailored MOF/MXene nanoarchitectures for developing novel high-performance counter electrodes for rechargeable Zn-air and Zn-ion batteries. The primary objectives of the project are given below;
(1) To develop different dimensional, highly porous, and high surface areas containing tailored MOFs and high-conducting MXenes for MOF/MXene nanostructures
(2) Nanoarchitectonics to optimize high-performance nanocomposite for improved electrochemical properties
(3) Using MOF/MXene nanostructures as electrode materials in Zn-ion/Zn-air batteries
(4) Development of prototype coin cell and pouch cell Zn-batteries
Different dimensional MOFs with variable metals and ligands will be synthesized. These MOFs will have no free coordination sites to provide the best stability with a wide range of solvents, pH conditions, and thermal and aqueous stability. The synthesized MOF will be directly composited with developed high-conducting MXenes (like V2CTx or Ti3C2Tx, etc.) by an in-situ synthesis process to grow MOF on conducting MXene layers. The electrochemical properties of the nanocomposite electrode will be thoroughly evaluated. The electrochemical oxygen evolution and reduction reactions (the main reactions at the air cathode responsible for the charging and discharging of the Zn-air battery) will be evaluated and optimized. The nanostructured composite electrode will be used to fabricate coin cell and pouch cell Zn-battery.
BITS Supervisor
Dr Chanchal Chakraborty
RMIT Supervisor
Prof. Nasir Mahmood
Required discipline background of candidate
| Discipline |
| Chemistry or Chemical Sciences |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Materials Chemistry |
|
Role of artificial intelliegence in designing circular supply chains
In response to the growing imperative for sustainability, supply chains are under increasing pressure to shift from linear to circular models. Circular supply chains, rooted in the principles of narrowing, slowing, and closing, prioritize minimizing raw material use, extending product durability, and maximizing recycling and reuse at the end of a product's life.
However, the actual shift from linear to circular supply chains is still in its early stages and requires further research. Prior research has indicated that the integration of artificial intelligence (AI) in supply chain operations can play a pivotal role in accelerating the implementation of circular supply chains. While the application of AI for accelerating circular supply chains theoretically makes sense, it remains unclear how AI capabilities support specific activities at different stages of circular supply chains. Moreover, it is still unclear what organizational readiness is required, the challenges that firms face, and the strategies to overcome such challenges to adopt AI for circular supply chains. This is mainly due to the lack of empirical exploration of the role of AI in circular supply chain design.
This research project, therefore, aims to empirically explore the role of AI in designing a circular supply chain model for manufacturing firms, with a focus on those critical for trade between Australia and India. The study will investigate how these firms, spanning various industries, can effectively adopt AI to shift from linear to circular supply chains.
The study will unfold in three phases. The first phase will encompass a comprehensive literature review to gain insights into the role of AI and the organizational capabilities required to adopt AI for circular supply chains. The second phase will involve gathering qualitative data from manufacturing firms to understand how these identified factors contribute to designing circular supply chains, the various challenges faced in the adoption of AI for circular supply chains, and ways to tackle those challenges.
Drawing on the insights from Phases 1 and 2, the research will develop a model with hypotheses to illustrate the mechanisms involved in adopting AI to shift from linear to circular supply chains. Finally, a large-scale survey will be conducted to test and validate the model, ensuring its applicability across diverse manufacturing sectors.
BITS Supervisor
RAJESH MATAI
RMIT Supervisor
Priyabrata Chowdhury
Other Supervisor RMIT
Kwok Hung Lau
Required discipline background of candidate
| Discipline |
| Climate |
| Data Science, Data Mining, Data Security & Data Engineering |
| MBA (Operations / Supply Chain and Logistics) |
| ME (Industrial/Production Engineering) |
| Sustainable Development, Development Studies, Development Geography, International Development |
|
Empowering Smart City Healthcare applications with Generative AI and Digital Twins
This project aims to explore the integration and application of Generative Artificial Intelligence (AI) and Digital Twin technology within the healthcare sector, specifically focusing on their potential to revolutionize medical research, diagnosis, and treatment methodologies. Generative AI, a cutting-edge technology capable of producing images, text, and various media forms from human prompts, holds significant promise in healthcare innovation. It can contribute to personalized medicine, predictive diagnostics, and tailored treatment plans. Concurrently, Digital Twin technology, which involves creating virtual replicas of physical entities, presents an opportunity to advance patient care by developing individualized digital counterparts. These digital twins can simulate patients' health conditions in real time, offering unprecedented insights into disease progression, treatment outcomes, and personalized healthcare interventions. Incorporating these technologies into the Smart City paradigm, this project envisions developing a robust healthcare system that leverages the capabilities of Generative AI and Digital Twin technology. This system will enhance patient care, improve health outcomes, and optimize resource allocation in future smart cities. By harnessing the synergy between these advanced technologies, the project aims to establish a healthcare framework that is innovative and responsive to the dynamic needs of urban populations, setting a new standard for healthcare delivery in the digital age.
BITS Supervisor
Vinay Chamola
RMIT Supervisor
Ibrahim Khalil
Required discipline background of candidate
| Discipline |
| Artificial Intelligence |
| Computer Science and Engineering/Computer Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
| Neural Networks |
|
International Trade in Services, female employment and entrepreneurship: An exploratory study of India and Australia
International trade in services holds a significant position in the trade portfolios of both India and Australia. According to the World Bank's 2024 estimates, service trade contributes 14.5% to India's GDP, and 9.6% to Australia's GDP. In December 2022, the two nations signed the Economic Cooperation and Trade Agreement (ECTA). A significant part of this agreement involves trade in services covering approximately 85 service subsectors. India's Female Labor Force Participation Rate (FLFPR) exhibited a concerning trend over the past few decades, declining from 33% in 1981 to a low of 20% in 2018. However, there has been a reversal in this trend, with the FLFPR rebounding to 35% in 2023. This resurgence can largely be attributed to the service sector, with approximately 64% of urban women in India having found employment in service sector in 2023. In contrast, Australia has consistently reported a positive trend, with FLFPR rising from 43% in 1979 to 62.8% in 2023. This sets the stage for exploring policy issues relating to the gendered impact of services trade on India's FLFPR and women entrepreneurship, and Australia's successful initiatives in this domain. This project is structured to investigate these key issues across three distinct phases. The first phase adopts a case-study approach, delving into the patterns of services trade pertaining to female employment and female entrepreneurship in both the countries. An ex-ante evaluation of the ECTA between India and Australia through a gender lens, utilizing Computable General Equilibrium Modeling is also part of this phase. The subsequent phase examines specific barriers and opportunities for female employees and entrepreneurs within service sectors relevant to international trade. This stage involves conducting quantitative analysis, employing applied econometric techniques such as Time-series modeling and Panel estimations. The first two phases rely on secondary data from international and national databases. The third phase incorporates qualitative analysis, including interviews or focus group discussions with few women employees and women entrepreneurs associated with sub-sectors participating in services trade. Focusing on Information Technology, Finance, Communications, Tourism, Healthcare, and Education, the project goal is to identify differences between the two countries and extract best practices for advancing gender outcomes in services trade.
BITS Supervisor
MINI THOMAS P
RMIT Supervisor
Ankita Mishra
Required discipline background of candidate
| Discipline |
| Banking, Finance and Economics |
| Business Analytics |
| Economics |
| MA in Development Studies |
| MBA (Operations / Supply Chain and Logistics) |
| MSc (with major subject Optimization) / MSc in Economics |
| Public Policy |
|
2D Chalcogenides Heterostructures Gas Sensors for Breath Marker Detection
Summery: In the current proposal, we are aiming to develop advanced and reliable gas/VOC sensors for breath marker detection. The advanced 2D materials are the broad alternative of the metal oxides in gas/VOC sensing applications. Their inherent advantages, such as single atom thickness which provides large effective surface area for molecular adsorption, low carrier concentration which can modulate conductivity easily due to adsorption of a few molecules of target analytes, high mobility which provides an exceptional fast carrier transport and finally the 2D materials having easy functionalization possibility. The gas sensing performance of 2D materials can be enhanced using dopants/ nanocomposite/ heterostructures by modifying the band structure, charge transfer mechanisms, physisorption, and surface reactivity, which enhances its capacity for gas adsorption.
Aims:
1. Chemical vapor deposition (CVD) growth of few layered 2D transition metal chalcogenides (TMDCs) e.g. MoSe2, WSe2, MoTe2 etc.
2. Integration of various oxide/sulfide materials with few layer TMDCs (selenides and tellurides) to develop various 2D heterostructures.
3. Morphological, structural and chemical characterizations of the pure and heterostructured 2D chalcogenides.
4. Fabrication of sensors/sensor array by implementing interdigitized noble metal electrodes on various substrates like SiO2/Si, Al2O3 etc.
5. Testing of sensing capabilities of the sensors in the exposure of popular breath markers gases/VOCs like NH3, acetone, NO, ethanol, CO, H2S etc.
Methodology: 2D chalcogenide synthesis will be performed with thermal and low pressure CVDs. A few layer/monolayer 2D selenides/tellurides will be oxidized under controlled oxygen ambient to introduced heterostructure like MoO3/MoSe2 with multilayer stack like structure. Controlled sulfurization of 2D selenides/tellurides will be implemented to develop MoS2/MoSe2 or WS2/WSe2 type heterstructures. The simultaneous use of two metal oxide sources or co-deposition of two different metals through DC sputtering and further sulfurization/ selenization through CVD route can provide different 2D heterostructures. As grown/synthesized 2D materials will widely be characterized using various in-house (RMIT/BITS) analytical techniques. To fulfill the requirement of sensor fabrication, both the institutes (BITS/RMIT) have state of the art fabrication facilities. The cutting edge gas sensing facilities are available with both the research groups.
BITS Supervisor
Prof. Arnab Hazra
RMIT Supervisor
Prof. Yongxiang Li
Required discipline background of candidate
| Discipline |
| Engineering, Engineering Physics |
| Materials Science |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Intelligent Procurement for Sustainable Supply Chain
An increased awareness of environmental, social, and economic impacts associated with business operations has driven supply chains towards sustainability. As supply chain links multiple functions, including logistics, production, procurement, and marketing and sales, an integrated end-to-end approach is essential. AIs capacity to analyze vast amounts of data and comprehend intricate relationships assists in developing sustainable supply chains by identifying opportunities to reduce waste, enhance transparency, and support ethical practices. Procurement function accounting for 50 to 80 percent of a company’s cost has potential to implement AI that drives sustainable supply chains (McKinsey, 2023).
Through scraping websites for data on finances, sustainability scorecards, diversity scores, and customer ratings of suppliers, AI has the potential to scout for new suppliers who are sustainable. Meanwhile, onboarding new suppliers is expensive and time-consuming. So, AI can be used to assess whether existing suppliers can provide additional materials. AI technologies can monitor existing suppliers' ethical and social practices by analyzing data related to labor conditions, human rights, and environmental impact. These practices ensures that suppliers are in align with environmental and social responsibility standards of supply chain. Moreover, adoption of AI in procurement process can increase organisation’s ROI through reducing the cost associated with procurement activities (KPMG, 2023). Given the importance of AI in procurement, industry professionals are looking for avenues of implementation while research is limited (Allal-Chérif et al., 2020; Guida et al., 2023). Hence, the aim of the research is to use AI based techniques such as genetic algorithm in driving procurement process towards sustainable supply chain.
In 2022-23, agriculture sector in India contributes 18.3% to the Gross Value Added(GVA) and has generated an export revenue of $50.2 billion (Economic Times, 2023). Despite the significance, the agricultural supply chain efficiency is impacted by the shortages of resources such as land, water, and soil health, along with exhausted work force. As a result, there is a growing pressure on Indian agriculture sector to move from resource-intensive methods to sustainable and environment-friendly farming practices. sustainable agriculture sector in India has a potential to emerge as a significant supplier to international markets seeking sustainability.
BITS Supervisor
Dr. Aneesh Chivukula
RMIT Supervisor
Dr. Aswini Yadlapalli
Other Supervisor BITS
Professor Srikanta Routroy
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Business Analytics |
| Data Science, Data Mining, Data Security & Data Engineering |
| MBA (Operations / Supply Chain and Logistics) |
|
Adversarial deep learning for robust LM-based systems
Generative AI has unprecented generative capability – e.g. media contents can include fluent language, realistic-like videos and image etc and such AI generated attacks present challenges to current AI/ML systems, which are also based on LLM or foundation models. This trend goes beyond textual, image and video data to other data types such as time series data. AI/ML automatic systems are also based on these foundation models – further fined-tuned either by additional layers or instruction-tune.
Pre-trained foundation models including Large language models (LLMs) and large models (LMs) for other types of data are increasingly used for artificial intelligence/machine learning (AI/ML) systems, especially for NLP and time series data applications. But research has shown that foundation models are susceptible to data noises and adversarial attacks. On the other hand, adversarial learning has the capacity to perform adversarial training and improve system robustness. In this project, you will research adversarial learning for improving the robustness of foundation models for complex applications. With pre-trained large models of billions of parameters, adversarial learning defence mechanism will be studied in a gray-box scenario with limited fine-tuning rather than full training to leverage the power within the trained AI model.
This project will likely comprise three parts: adversarial evaluation of the robustness of foundation models; few-shot adversarial learning to fine-tune foundational models and zero-shot adversarial learning. We will produce research, design, development, and innovations in the Adversarial machine learning (AML), Adversarial artificial intelligence (AAI), and Adversarial deep learning (ADL). Latent space on high dimensional training data can be searched to construct adversarial examples. Depending on the goal, knowledge and capability of an adversary, adversarial examples can also be constructed for foundation models. They can also be crafted by prior knowledge, observation, and experimentation on the loss functions in machine/deep learning. They are useful to simulate computational optimization and statistical inference problems in deep learning. Furthermore, adversarial examples are known to transfer between data-specific manifolds of deep learning models. We will address algorithmic bias in AI application domains consisting of adversarial examples by integrating generative adversarial learning algorithms with foundation models.
BITS Supervisor
Dr. Aneesh Chivukula
RMIT Supervisor
Professor Jenny Zhang
Other Supervisor BITS
Dr. Manish Kumar
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
|
1. Towards Greener and Safer Construction: Seismic Response of Masonry Infill Walls made using Ni-Cr Plating Sludge
Background and Motivation :
The construction industry plays a pivotal role in the global economy, yet it faces with challenges such as
seismic resistance and the escalating burden of industrial waste disposal. In seismic-prone regions, the
assessment of structural components' integrity under seismic loads is important for ensuring the safety of
buildings and infrastructure. Masonry infill walls, a common feature in construction, are often susceptible to
seismic events, particularly in regions lacking adequate seismic-resistant design considerations.
The motivation for this research appears from the critical need to address these challenges while
simultaneously tackling the environmental impact of industrial waste. Nickel-Chrome Plating Sludge (NCPS),
a byproduct of chrome plating demand, is a substantial industrial waste with significant environmental
implications. Conventional disposal methods, such as landfilling, pose environmental risks and strain
available land resources. This research seeks to innovate waste strategies by incorporating NCPS into Fired
Clay Bricks (FCBs), exploring the dual benefits of waste reduction and sustainable construction practices.
Moreover, the project aligns with the imperative to enhance seismic resilience in urban areas, especially those
located in low to moderate seismic hazard regions. The prevalent non-ductile designs of masonry infill wall
systems and the absence of robust seismic-resistant considerations contribute to the vulnerability of structures.
By investigating the seismic performance of FCBs with NCPS in masonry infill walls, the project aims to
contribute not only to structural engineering knowledge but also to the development of environmentally
conscious and resilient construction practices.
Objectives :
1. Investigate the seismic behavior of masonry infill walls incorporating Nickel-Chrome Plating Sludge
(NCPS) bricks.
2. Assess the structural integrity under seismic loads, emphasizing the resilience of the components.
3. Explore innovative strategies for the NCPS, a significant industrial waste, by incorporating it into
Fired Clay Bricks (FCBs).
4. Evaluate seismic risk in urban areas located in low to moderate seismic hazard regions.
5. Explore the reduction of the carbon footprint in construction by incorporating waste materials,
aligning with global environmental objectives.
Methodology :
The methodology outlines a systematic approach to investigate the seismic behavior of masonry infill walls
inc
BITS Supervisor
Dipendu Bhunia and Professor
RMIT Supervisor
Prof. Guomin (Kevin) Zhang
Other Supervisor RMIT
A/Prof Ricky Chan
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
| Construction Eng/Management and Materials |
| Design, Design Engineering, Sustainable Design |
|
AI-Empowered Dynamic Resource Allocation in Integrated Ground-Air-Space Communication Networks
The project aims to develop advanced artificial intelligence (AI) and machine learning (ML) algorithms to drive dynamic resource allocation in integrated ground-air-space communication networks. By harnessing state-of-the-art wireless technologies—millimeter-wave (mmWave), free-space optical (FSO), and terahertz (THz)—the initiative leverages AI to autonomously optimize spectrum usage, mitigate interference, and adapt to rapidly changing channel conditions in real-time.
The primary objectives of the project are as follows:
(a) Innovative Protocols and Algorithms:
Design and implement cutting-edge AI and ML algorithms tailored to the unique characteristics of mmWave, FSO, and THz technologies, ensuring seamless integration and optimal network performance.
(b) Advanced Spectrum Allocation Solutions:
Develop robust solutions for shared spectrum challenges by pioneering innovative allocation strategies, employing deep learning for interference prediction and mitigation, and utilizing adaptive radio channel techniques to maintain reliable communication links.
(c) Intelligent and Autonomous Systems:
Create smart algorithms that dynamically optimize spectrum use, adjust transmission parameters in real-time, and counteract interference by continuously adapting to evolving environmental and network dynamics through AI-driven insights.
(d) Innovative Methodologies for Future Networks:
Explore novel approaches to spectrum management, interference mitigation, and dynamic resource allocation powered by AI, with significant potential for disaster response, surveillance, and remote sensing applications.
The methodology involves extensive simulations, mathematical modeling and analysis, and the validation of AI/ML algorithms using real-time empirical data. Through this comprehensive research and development effort, the project aspires to redefine the capabilities of integrated ground-air-space networks, paving the way for a more resilient and efficient communication infrastructure.
BITS Supervisor
Syed Mohammad Zafaruddin, Associate Professor
RMIT Supervisor
Akram Hourani, Professor
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Electrical and Electronics Engineering, Power Engineering |
| Information Technology |
| Mathematical Sciences |
| Networks and Communications, Wireless Comms, Telecommunications |
| PHYSICS |
|
Battery Thermal Management with Cold Plates made of Triply Periodic Minimal Surface (TPMS) for EVs
Electric vehicles (EVs) have been considered an efficient solution to alleviate the intensifying energy and environmental crisis. Due to the high energy density, long cycling life, and high efficiency, lithium-ion batteries (LIBs) are selected as the primary power source for EVs. However, the performance of the LIBs is greatly affected by their operating temperature. During the charge and discharge processes, LIB's reasonable working temperature range is 25–40 ?C, and the temperature difference of the battery module should be within 5?C. The power capacity of the LIB decreases at low temperatures, while the risk of thermal runaway increases at high temperatures. Therefore, a battery thermal management system (BTMS) is significant in ensuring the thermal safety of the battery and enhancing the battery's electrical performance in the operating process.
According to the different cooling mediums, BTMS can be classified into three methods: air cooling, liquid cooling, phase change material (PCM), and a combination of them. Although the PCM increases the installation space, weight, and cost of the BTMS, the higher thermal conductivity of PCM-based hybrid cooling excels in its efficacy over the air or liquid cooling approaches. As the PCM experiences continuous phase changes, an innovative cold plate design is essential to encapsulate the PCM and maximize the heat transfer.
Therefore, it is decided to indigenously design a triply periodic minimal surface (TPMS) based cold plate to encapsulate the PCM.
The following objectives are proposed to investigate the thermal management system of lithium-ion batteries integrated with TPMS structures.
• Numerically explore the ideal cold plate design for battery thermal management using various sheet-based TPMS structures.
• Development of TPMS structures-based cold plates for thermal management of Li-ion battery pack.
• Explore the durability and thermal stress of the cold plate for volatile operating conditions.
• Explore the performance enhancement during hybridization of the cold plate with phase change materials for thermal management of the battery pack.
BITS Supervisor
Santanu Prasad Datta
RMIT Supervisor
Dr. Maciej Mazur Senior Lecturer
Other Supervisor BITS
NITIN RAMESHRAO KOTKUNDE
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Developing a threat model for organisations through a gamified approach to thwart phishing attacks
Summary of the proposed project: Phishing is well known as online identity theft, which aims to steal sensitive information such as username, password, and online banking details from its victims. Automated anti-phishing tools have been developed and used to alert users of potentially fraudulent emails and websites. However, these tools are not entirely reliable in detecting phishing attacks. Because of the sensitive trust decisions made by humans during their online activities. It is not possible to completely avoid the end-user, one mitigating approach for cyber security issues is to educate and train the end-user in security prevention However, previous research has revealed that education alone is insufficient to combat against phishing threat. This is mainly because the knowledge and skills gained through cyber security education and training programmes do not necessarily reflect on people’s online behaviour. On the other hand, cyber-criminals will leverage their attack against the organisation through the human vulnerability (i.e., human weaknesses). In this project, a serious game developed through understanding human cognition, encouraged users to enhance people’s avoidance behaviour through motivation to protect themselves from phishing attacks. Therefore, the aim of this project proposal focuses on developing a threat model for organisations through a gamified approach to thwart phishing attacks. In this project, the game is employed to collect and understand users’ (i.e., game players in this case) strategies to differentiate phishing attacks from legitimate ones through the game. Finally, the project will develop a threat model understanding how cybercriminals leverage their attacks within the organisation through the human exploitation.
Outcomes: The developed threat model can be used to develop countermeasures (i.e., both technical and non-technical) and educational interventions to the organisation. The proposed gamified approach will not only enable the both governments (i.e., India and Australia) and organisations to educate and train their citizens against phishing crimes, but also develop a threat model understanding how cybercriminals leverage their attacks within the organisation through the human exploitation.
BITS Supervisor
Jagat Sesh Challa, Assistant Professor
RMIT Supervisor
Nalin Asanka Gamagedara Arachchilage
Required discipline background of candidate
| Discipline |
| Computing: Collaborative and Social Computing, Computing Education, Computer Systems,Human Computer Interaction |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Public Policy |
|
Surface Modifications for Sustainable Energy Production
With the rise in energy demand, exploring efficient and economical ways of sustainable energy production techniques to reduce our dependency on fossil fuels, the primary source of the global greenhouse effect and climate change is essential. The energy requirement perceived an unparalleled growth in renewable energy production, with wind energy as a leader among others. In 2019, 7.3% of U.S. energy requirements were met by wind energy, with that percentage forecasted to increase to 20% by 2030 and 35% by 2050. In the wind turbine system, the mechanism involves the rotation of the rotor, which is directly connected to a generator through different bearings and a series of gearboxes (which speed up the rotation). The transition of wind energy to the rotation of a generator is what produces electricity. The premature failures (i.e., surface-initiated fatigue, white etching cracks [WECs], scuffing/smearing, spalling, and dents/indentations) of bearing in wind turbines are the prime concerns and significant causes of downtime in energy production.
For this reason, the project aims to develop a high entropy alloy (HEA) coating with constituent elements of equal molar ratio, which will be fabricated using the magnetron sputtering technique. The investigating hypothesis will be the effect of metal disulfide content on the microstructure, composition, phase constitution, and wear and corrosion phenomenon on the magnetron sputtering HEA coatings.
A tribological system consists of two same/different materials rolling/sliding against each other in dry or lubricating conditions. The investigating hypothesis will be how HEA hard-coated and lubricated tribological pairs could improve the endurance limit of the wind turbine bearings. In this, the P.I. aims to develop a hard and lubricated coated tribological pair that can support heavy axial and radial turbine load with minimum friction. The principal investigator will focus on developing an advanced tribological system consisting of Titanium alloy-coated bearing rollers in linear contact with the metal disulfide-coated raceways in dry and lubricated rolling conditions. The lubricant incorporated with metal disulfide nanoparticles as a friction modifier will be further tested for its auxiliary lubricating behavior in lubricated conditions.
Thus, developing and investigating effective and economically advanced tribological systems for wind energy turbines for controlling turbine bearing failures are highly desirable.
BITS Supervisor
Piyush Chandra Verma
RMIT Supervisor
Prof. Nasir Mahmood
Other Supervisor BITS
Himanshu Aggarwal
Other Supervisor RMIT
Prof Raj Das
Required discipline background of candidate
| Discipline |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Materials Chemistry |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Engineering |
|
Photocatalytic Green Hydrogen Production and Its storage
To fulfill the continuously growing need for energy that will not adversely affect the environment, hydrogen has been found to be a clean fuel with zero carbon emissions. However, the conventional hydrogen generation methods leave a carbon footprint. The proposed project aims to generate green hydrogen using photocatalytic water splitting and the consequent development of a hydrogen storage system. A photocatalyst will be designed through density functional theory and will be synthesized experimentally. A nanoporous material for efficient hydrogen storage will be predicted through machine learning, and the adsorption capacity of the porous material will be predicted using molecular simulations. Finally, the project will develop a complete hydrogen generation and storage system for utilization of hydrogen as a clean fuel in our daily life.
BITS Supervisor
Dr. Sarbani Ghosh - Assistant Professor
RMIT Supervisor
Rachel Caruso
Other Supervisor BITS
Mohit Garg
Other Supervisor RMIT
Dr Haoxin Mai
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Engineering, Engineering Physics |
| PHYSICS |
|
Catalytic polymer composite systems for environmental applications
Environmental pollution is a global phenomenon. There are different types of pollutants, among which organic chemical contaminants (phenolic compounds, petroleum, pesticides, pharmaceuticals, etc.) may adversely affect the ecosystem and induce microbial resistance to antibiotics. Various remediation techniques have been applied for organic contaminants in water; however, adsorption with catalytic activity can be considered one of the most promising due to several environmental and techno-economic merits, and sometimes, such techniques may produce value-added chemicals from the pollutants. To identify the optimal material for organic chemical degrading might be challenging. Polymer nanocomposites (PNCs), combining the benefits of nanoparticles with polymers, may open up new possibilities for overcoming this difficulty [1].
References
1. https://doi.org/10.1016/j.scitotenv.2023.165772
2. https://doi.org/10.1016/j.jenvman.2022.116596
3. https://doi.org/10.1002/slct.201900470
The global surplus agro-residue (AR) generation rate is around 3300 MT, which is underutilized and could be a cause of environmental pollution for stubble burning. We aim to utilize this AR to synthesize high surface area and porosity carbonaceous materials (AC, GO) and then use those as a part of the nanocomposite with polymer to adsorb the pollutants. Nanoscale range zero-valent transition metals or their bimetallic compositions are highly efficient in eliminating different pollutants present in our external environment [2]. Those nanoparticles would be immobilized in some polymers to allow them to react with the targeted contaminants while inhibiting their reactivity with the surroundings [3]. Soil and/or water remediation will be the target of this work.
BITS Supervisor
Prof. Banasri Roy
RMIT Supervisor
Dr. Fugen Daver - Associate Professor
Other Supervisor BITS
Mohit Garg
Other Supervisor RMIT
Namita Roy Choudhury
Required discipline background of candidate
| Discipline |
| Chemical Engineering |
| Chemistry or Chemical Sciences |
| Materials Chemistry |
| Physics, Condensed Matter Physics |
|
Virtual Reality Assisted Robots for Civil infrastructure Inspection
Aim: To create a VR based digital twin of a Robot that can be used in the construction industry for inspection
Methodology:
The demand for infrastructure inspection using autonomous robots is rising, with ground robots offering high payload capacity and power efficiency. They can integrate multiple sensors for structural assessment.
Sensor Technologies for Inspection: Vision sensors are energy-efficient and useful for crack and displacement detection, while range sensing (e.g., LiDAR) provides higher accuracy but requires more computational power for precise structural assessments.
Ground Robotic System & AI Integration: The proposed inspection platform integrates LiDAR and cameras, using the Robot Operating System (ROS) with deep learning for 3D mapping, damage localization, and visualization, reducing the need for manual tuning.
Role of Digital Twin & Virtual Reality: Digital twins provide a real-time virtual model of the system for optimization and modification. VR enables remote robot operation for safer infrastructure inspections and serves as a training tool for operators.
Simulation for Optimization: Using Unity 3D, Nvidia Isaac, and ROS, a digital twin will be created to simulate real-world environments. Deep learning-based object detection will enhance performance, predict errors, and optimize robot deployment before real-world testing.
Real-time Validation: The proposed system will be tested in real-time for infrastructure inspection and the performance will be evaluated.
BITS Supervisor
Dr.V.Kalaichelvi, Professor
RMIT Supervisor
Dr Ehsan Asadi
Other Supervisor BITS
Prof.R. Karthikeyan
Other Supervisor RMIT
Dr Debaditya Acharya
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Exploring 2D Metal Oxides and Dichalcogenides for Advanced electronics and Optoelectronic Device Applications
The rapid evolution of electronics, optoelectronics, and sensing technologies has been fueled by atomically thin materials with exceptional optical and electronic properties. This study focuses on developing 2D metal oxides and metal dichalcogenides using a liquid metal framework to fabricate ultra-thin structures for broadband photodetection, resistive switching, and gas sensing. These materials exhibit high carrier mobility, tunable bandgaps, and superior stability. The research primarily targets Ga, Ni, and Mo-based compounds, with potential extensions to alternative materials.
Structural and optical properties of the 2D material will be analyzed using XRD, HRTEM, photoluminescence, Raman spectroscopy, and UV-vis absorption spectroscopy. The electronic characteristics of 2D layers will be evaluated via FET mobility measurements to optimize charge transport and device performance.
Potential Applications
Broadband Photodetectors: This project aims to develop 2D heterostructures using semiconducting transition metal dichalcogenides (TMDCs) and hexagonal boron nitride for broadband photodetection. The ratchet effect in nanostructured arrays enables strong directed current generation without an external force, overcoming traditional photodetector bandgap limitations.
UV Photodetectors: Wide and ultrawide bandgap 2D metal oxides will be synthesized for UV detection across UVA, UVB, and UVC bands (200–400 nm). The liquid metal-based method ensures cost-effective fabrication, avoiding the complexities of ALD, PLD, and MBE techniques. These 2D films will be integrated into interdigital photoconductors and bottom-gate transistors, benchmarked against existing UV detectors based on responsivity, detectivity, and time response.
Metal Oxide-Based Resistive RAM (ReRAM): Transition metal oxides (HfO2, TiO2, ZnO) will be explored for non-volatile memory applications due to their high-speed operation, low power consumption, and CMOS compatibility. Growth of oxide thin films will be optimized for improved switching uniformity, endurance, and retention. Electrical, structural, and spectroscopic analyses will investigate oxygen vacancy migration and redox reactions.
BITS Supervisor
Ramesh Vasan
RMIT Supervisor
Professor Sumeet Walia
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Materials Science |
|
Machine learning assisted development of advanced nanocomposite materials for CO2 capture
The increasing amount of CO2 emission in the atmosphere and its effect on the ecosystem has posed a serious concern, globally. Therefore, developing technologies for effectively reducing CO2 is a need of time. Amine-based absorption is the most developed and well-demonstrated among the available options. However, it is an energy-intensive process. Therefore, efforts are being made towards developing alternative composite materials for CO2 capture. The present work proposes a machine learning assisted synthesis approach of advanced nanocomposites, particularly, metal-organic frameworks-based materials for carbon capture application.
The specific objectives of the proposed work are as follows:
1. To develop machine learning models in identifying the optimum synthesis conditions
2. To synthesize and characterize a series of advanced composite materials
3. To evaluate the carbon capture activity of the synthesized materials
4. To study the effect of various operating parameters (such as flow rate, temperature, pressure, presence of impurities, etc.)
5. To determine the underlying reaction mechanism.
Methodology:
1. Machine learning models will be developed and used for the synthesis of nanocomposite MOF-based materials with varying ratio of individual component in the composite.
2. The synthesized materials will be characterized for surface area, pore size, pore volume, surface morphology, elemental analysis, thermal stability and particle size using porosimeter, scanning electron microscope, thermogravimetric analysis and particle size analysis.
3. The effect of various parameters (such as flow rate, temperature, pressure, presence of impurities, etc.) on CO2 adsorption will be evaluated in the presence of synthesized composites.
4. Based on results and physico-chemical analysis of the spent material, an underlying mechanism will be proposed.
BITS Supervisor
Sharad Sontakke
RMIT Supervisor
Dr. Ravichandar Babarao
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Fake or Fact? Detecting and Mitigating AI-Generated Fake Content
AI-generated fake content poses severe risks in domains like journalism, cybersecurity, and digital forensics. This project aims to develop an end-to-end framework for the detection and mitigation of AI-generated fake content across multiple modalities, including text, image, and video. The primary objective is to develop detection algorithms using deep learning, feature engineering, and adversarial training to distinguish synthetic content from authentic data with high precision. The project will also explore countermeasures to mitigate the impact of such content through watermarking, model explainability, and content provenance tracking.
The methodology involves analyzing datasets from diverse generative models(including text-based outputs from LLMs), synthetic images (from GANs and diffusion models), and deepfake videos. Feature extraction techniques will be employed to identify statistical, spatial, and temporal inconsistencies, such as unnatural texture patterns in images, linguistic anomalies in text, and physiological inconsistencies in videos. Detection models will be trained using transformer-based architectures such as Vision Transformers for images, RoBERTa for text classification, and spatiotemporal networks for videos. Adversarial testing will be conducted to enhance model robustness against adversarial attacks that attempt to bypass detection. For mitigation, the research will integrate AI-generated watermarking techniques to embed imperceptible but detectable signatures within synthetic content. Blockchain-based provenance tracking will also be explored to authenticate content sources. The ultimate goal is to develop a scalable AI-powered detection and mitigation tool capable of generalizing across different generative models while minimizing false positives and computational overhead.
BITS Supervisor
Vinay Chamola
RMIT Supervisor
Professor Feng Xia
Required discipline background of candidate
| Discipline |
| Artificial Intelligence |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computer Science/Information Technology |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
|
Protein-based nanoparticles for oral drug delivery
This PhD project aims to advance innovative strategies for fabricating biocompatible protein nanoparticles using novel ionic liquids and salts. The primary focus is on dissolving and desolvating food-based proteins, such as ovalbumin, serum albumin, and lactalbumin, to produce nanoparticles or nanogels suitable for oral delivery of bioactive compounds. This research seeks to revolutionize oral therapeutic delivery systems by addressing challenges in permeability and stability.
The project will develop ionic liquid solvents, or their mixtures with ethanol, as biocompatible solvents, and understand their influence particle formation in aqueous protein solutions, where they can induce spherical or fibroin nanoparticles. To optimize nanoparticle production, various ionic liquids will be employed to fine-tune the desolvation process. This project will study the desolvation factors, e.g., crosslinking agents, salt types, and the concentration of proteins, and correlate them with particle size and morphology. The advanced methodology will integrate small-angle X-ray scattering (SAXS) at the Australian Synchrotron to characterize particle structures, providing insights into their size, shape, and assembly mechanisms. Ultimately, this project aims to develop tailored formulations with enhanced bioavailability and targeted delivery capabilities, laying the groundwork for transformative applications in oral therapeutics and beyond. The findings will have broad implications for nanoparticle engineering and developing innovative drug delivery platforms.
BITS Supervisor
Dr. Ankit Jain
RMIT Supervisor
Dr. Hank Hank
Other Supervisor BITS
Dr. Gautam Singhvi
Other Supervisor RMIT
Prof. Tamar Greaves
Required discipline background of candidate
| Discipline |
| Chemistry |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Pharmaceautical Sciences, Pharmacology |
| Pharmaceutical Sciences |
|
Fully Printed Piezoelectric Sensors for Advanced Health Monitoring and Robotic Applications
The high prevalence of cardiovascular diseases in middle-aged populations calls for advanced continuous monitoring technologies. Traditional methods are costly, while wearables like the Apple Watch offer 80-85% accuracy, limiting clinical reliability. To achieve 95-99% accuracy, this project explores high-sensitivity alternatives, including continuous wearable ultrasound imaging for real-time blood flow monitoring, paving the way for more precise and reliable cardiovascular health tracking.
By integrating advanced material engineering, surface modification, and optimized charging techniques, the goal is to create flexible, long-lasting piezoelectric materials that maintain stable performance under varying body temperature and humidity conditions. To achieve this, thin micro/nanoporous piezoelectric sensors will be fabricated using flexible sustainable polymers, and cellulose-based materials, hydrophobic properties for enhanced durability. A fully printable approach utilizing screen printing, direct ink printing or both will be developed to precisely pattern piezoelectric and electrode materials, ensuring scalability and cost-effectiveness. Charge trapping within polymer void structures will be enabled through a custom-built corona discharge system and pyroelectric charging process. The sensors will be characterized, with longitudinal and transversal piezoelectric coefficients measured to assess performance. Durability testing will evaluate bending resistance, mechanical flexibility, and the minimum curvature radius to ensure long-term reliability.
The developed sensors will capture high-fidelity bioelectrical signals to monitor cardiac parameters like heart rate, arrhythmias, and blood pressure accurately. Flexible piezoelectric sensors will be used to detect subtle cardiac pressure changes with high sensitivity. Noise reduction techniques and signal conditioning will be used to minimize motion artifacts and interference. For real-time blood flow monitoring, flexible piezoelectric ultrasound transducers will be integrated and calibrated using tissue-mimicking phantoms. In robotic wearables, developed flexible piezoelectric pressure and strain sensors will be used to improve motion detection and adaptive control in prosthetics and exoskeletons. Additionally, multi-channel sensor arrays will be used to enable simultaneous monitoring of physiological signals, providing comprehensive health insights and enhancing diagnostic accuracy for personalized treatment
BITS Supervisor
Vinaya Kumar K B
RMIT Supervisor
Prof. Madhu Bhaskaran
Other Supervisor BITS
Tushar Sakorikar
Required discipline background of candidate
| Discipline |
| Biomedical Sciences |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Physics, Condensed Matter Physics |
|
Soft Tissue Characterisation
Soft tissue’s mechanical properties are important to many modern applications of technology to medicine, such as robotic surgery, soft tissue modelling and surgical simulation with force feedback. As acoustic signals are sensitive to tissue mechanical properties, this project aims to characterise the mechanical properties of soft tissue (such as Young’s modulus, Poisson’s ratio and damping coefficients) from acoustic signals. Acoustic waves will be acquired from ultrasound imaging and/or a robotic vibration system, both of which are available in Dr Zhong's research lab at RMIT University. Based on analysis of the characteristics of acoustic signals (including signal denoising), biomechanical modelling (such as finite element modelling) will be established to describe the relationship between acoustic waves and tissue mechanical properties. Subsequently, online numerical algorithm (such as Kalman filter) will be developed to identify tissue mechanical properties from acoustic waves. Experiments will be conducted on phantom tissue samples available within Dr Zhong's research lab. These tissue samples are made from silicon with the similar mechanical properties as biological soft tissue.
It should be noted that this project is mainly on developing a biomechanical model and Kalman filtering algorithm, rather than on using software.
BITS Supervisor
Venkatesh Kadbur Prabhakar Rao
RMIT Supervisor
Yongmin Zhong
Required discipline background of candidate
| Discipline |
| Mathematical Science |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Dynamic Modelling of Soft Tissue Deformation
Virtual reality based surgery simulation is expected to provide benefits in many aspects of surgical procedure training and evaluation. Surgery simulation requires soft tissue reacts to the applied forces in a realistic fashion and in real time. However, it is difficult to handle both of these conflicting requirements, and thus modelling of soft tissue deformation is a challenging research topic in surgery simulation. This project aims to study the fundamental issues associated with soft tissue deformation for surgery simulation. It will develop advanced physical models based on continuum mechanics, and real-time algorithms for dynamic modelling of nonlinear deformation behaviours of soft tissue for surgery simulation. Simulation and experimental analyses will also be conducted for verification and validation purposes.
BITS Supervisor
Venkatesh Kadbur Prabhakar Rao
RMIT Supervisor
Yongmin Zhong
Required discipline background of candidate
| Discipline |
| Mathematical Science |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Modulation of soil microbiome by microplastics: implication for food security
Background and aim: The pervasive presence of microplastics (plastic particles with <5mm in size) in soil from anthropogenic practises (such as modern agriculture) is a global sustainability issue. Microplastics and their associated additives can alter/stress soil microbiome, potentially impacting the beneficial interactions between plants and plant-associated beneficial rhizobacteria, which are crucial for stress tolerance and nutrient uptake by plants/crops. This research aims to investigate the interplay between microplastics, soil microbiomes, and plants, focusing on the modulation of beneficial plant-rhizobacterial interactions under microplastics-induced stress scenarios. The overall objectives of this PhD are to: 1) analyse the effects of microplastics on the diversity and composition of soil microbiomes; 2) assess how changes in soil microbiomes influence beneficial plant-rhizobacterial interactions; and 3) evaluate the role of these interactions in enhancing plant stress tolerance in the presence of microplastics.
Methodology: This study will involve both controlled laboratory experiments and field studies and leverage multi-omics and advance molecular techniques. Soil samples will be collected from various agricultural sites with environmentally realistic microplastics contamination. A set of controlled experiments will be initiated in a greenhouse, where plants will be grown in soils with varying concentrations of microplastics.
Soil microbiome composition will be assessed using high-throughput sequencing techniques, such as 16S rRNA gene sequencing and metagenomics. This analysis will provide insights of impact of microplastics on composition and functional potential of soil microbial communities.
Integrated transcriptomics and metabolomics study will be conducted to elucidate the underlying molecular mechanism of the biological responses of soil microbiomes and plants to microplastics. A known model crop such as rice will be used for the plant-based studies. Inter-relation between microbial community composition and the fingerprint of dissolved organic matter in the rhizosphere will be performed to estimate whether the “below-ground changes” have far-stretching consequences on “above-ground” plant performance, under the exposure of microplastics. Specific attention will be given to rhizobacteria known for their beneficial interactions with plants, such as nitrogen-fixing bacteria (e.g., Rhizobium spp.).
BITS Supervisor
Sridev Mohapatra
RMIT Supervisor
Tanveer Adyel
Required discipline background of candidate
| Discipline |
| Agriculture |
| Bioinformatics |
| Biotechnology |
| Genetics, Epigenetics, Genetic Engineering |
|
Design and Development of Flexible Antennas for Health Monitoring Sensing Devices
The demand for wearable and flexible electronics has surged due to advancements in healthcare monitoring systems. Wearable sensing devices require efficient communication for accurate data transmission, with flexible antennas playing a vital role in ensuring connectivity. The project "Design and Development of Flexible Antennas for Health Monitoring Sensing Devices" aims to address the challenges of integrating high-performance antennas into wearable health systems.
The key objectives include investigating flexible materials such as conductive fabrics, polymers, and liquid metals to enhance conductivity and durability. Additionally, optimizing antenna performance for efficiency, low return loss, and stable frequency response under deformation is crucial. The project focuses on seamless integration with wearable health sensors, ensuring biocompatibility, comfort, and wireless communication performance.
The methodology involves material selection and characterization, including evaluating electrical and mechanical properties. Antenna design and simulation use CST Microwave Studio and HFSS to develop microstrip patch, monopole, dipole, and PIFA antennas. Advanced fabrication techniques such as screen printing, inkjet printing, and 3D printing are utilized. The durability of antennas is tested under bending, stretching, and environmental exposure.
Integration with health monitoring devices ensures stable adhesion to textiles or skin patches, compatibility with Bluetooth and NFC, and minimal interference with physiological signals. Testing involves real-world assessments of wireless communication range, stability, data accuracy, and performance under body movements. The flexible antennas are compared to rigid alternatives for efficiency, reliability, comfort, and interference resistance.
This project has significant implications for healthcare, improving patient monitoring, wearability, and wireless connectivity. It enhances biomedical research and facilitates telemedicine advancements while ensuring scalability for commercial applications. The research aims to revolutionize wearable health technology, leading to more efficient and reliable health monitoring systems, ultimately improving patient care and remote health management.
BITS Supervisor
Sudeep Baudha
RMIT Supervisor
Wayne Rowe
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Machine Learning Driven Digital Twin Enabled Microgrid for Sustainable Energy Management
1. Introduction:
The need for affordable, reliable, sustainable, and modern energy has never been more urgent due to rising global energy demands and the transition to renewables. Traditional energy systems struggle with efficiency, scalability, and adaptability. This project proposes a Digital Twin (DT)-enabled microgrid to enhance resilience, reliability, and efficiency across urban, rural, and industrial applications. DTs simulate diverse operating conditions, while machine learning (ML)/artificial intelligence (AI) models analyze this data to optimize energy forecasting, operation, and decision-making. An ML-driven DT-enabled microgrid enhances energy management through real-time analytics, predictive modeling, and advanced automation. This integration improves operational efficiency, sustainability, and cost-effectiveness, ensuring a more resilient energy system. ML further strengthens adaptability and scalability, facilitating the transition to a sustainable energy future.
2. Problem Statement:
Modern power distribution systems must evolve to integrate distributed energy resources (DERs) like solar, wind, and battery storage. Traditional grids lack real-time monitoring and adaptive control, causing inefficiencies. A DT-enabled microgrid addresses these issues by simulating emergency scenarios, optimizing operations, and enabling real-time adjustments. With capabilities such as predictive maintenance and intelligent decision-making, DT technology enhances grid stability and performance.
3. Objectives:
1. Develop an intelligent microgrid with DT technology, IoT, and cloud-based analytics for real-time monitoring and control.
2. Improve energy efficiency through optimized operations and resource utilization.
3. Utilize ML/AI-driven decision-making to balance energy supply and demand.
4. Implement predictive maintenance for system longevity and cost efficiency.
4. Methodology:
The project will be executed in phases:
1. Integrate DERs such as solar, wind, and battery storage.
2. Install sensors on solar panels, wind turbines, batteries, and meters to collect real-time energy data.
3. Mirror the physical microgrid to enable real-time analysis, fault detection, and automated control.
4. Process DT and physical system data to train ML models for energy optimization using cloud-based analytics.
5. Optimize energy distribution across generation, storage, and loads.
6. Simulating various operational scenarios to evaluate system performance and scalability
BITS Supervisor
HITESH DATT MATHUR
RMIT Supervisor
Dr. Kazi Hasan
Other Supervisor BITS
Dr. Alivelu Manga Parimi
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
|
Modification of QCM surface using stimuli-responsive materials to afford sensitive and selective devices for toxic vapor detection
We focus on the economical synthesis of simple functionalized organic molecules possessing a large surface area and superb porosity. Various substituents will tune the molecular conformation/twisting to yield intense solid-state emitters. Thus, well-defined and decorated organic molecules will be appropriately tailored to detect various toxic volatile analytes having a societal impact on the environment (C6H6, HCHO, CH2Cl2, MeCOMe, alkenes, C3H8, CH4, CO2, R-OH, etc.) and food sectors (NH3, 1,3-diaminopropane, putrescine, cadaverine etc.). The inclusion of -OMe, -COOH, -NH2, and conformationally deformed molecular units (phenothiazine/triphenylamine) would be suitable to offer stimuli-responsive features by tuning weak noncovalent interactions. Monitoring hydrophobicity/hydrophilicity and enabling photo-induced electron transfer in the molecular design are vital. The volatile analytes can change the microenvironment of the emitters or undergo reversible chemical reactions with active sites to cause absorption and emission changes.
Such emissive stimuli-responsive materials will be coated on a piezoelectric surface, such as quartz crystal microbalance (QCM), a mass-sensitive platform to detect vapors. Such modified QCM surfaces would be more selective and sensitive against vapors through frequency signal changes (due to changes in surface mass) and visually detectable color. Thin film variation, film thickness, conductivity, temperature, and vapor adsorption capacity on the surface will be scrutinized to gain better insight into the interaction mechanism and correlate mass changes to color changes. FT-IR/SEM/PXRD/BET studies will characterize the coated surface to investigate vapors' adsorption, diffusion, and desorption processes. As the QCM surface is sensitive to mass changes, a stimuli-responsive molecular layer would be more beneficial even if the gas vapors get trapped on the surface or undergo chemical reactions. The QCM technique can provide sorption kinetics data, response time, the limit of detection, and selectivity, which will provide insight when studying color change due to molecule-surface interaction. The reusability of the surface will be achieved by surface washing or automatic evaporation of low-boiling side products. Thus, we aim to generate handy platforms using thin film of stimuli-responsive emitters on the QCM surface and exposing them to various vapors (control the air pollution) or crucial amine vapors (measure food’s freshness).
BITS Supervisor
Manab Chakravarty
RMIT Supervisor
Samuel Ippolito
Other Supervisor RMIT
Dr Ylias Sabri
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Design, Design Engineering, Sustainable Design |
|
Green technology for mitigating sulfur emission from fuels using microbial biopolymers and nanozyme based materials
Sulfur content in fuel is a major threat to the environment as it results in SOx emissions on account of fuel combustion. Desulfurization is a major step in fuel processing since in crude oil sulfur is majorly found in its soluble organic forms. The aromatic compounds in fuel, including thiophene and its derivatives, are more stable, non-polar and hard to mitigate from fuel through conventional high-temperature hydrodesulfurization. Adsorptive desulfurization is one of the alternative methods for desulfurization that can be tailored for scale-up operations. Bio-desulfurization is process where microbes/enzymatic compounds are used as catalysts for desulfurization of fuel. Herein, the microbes target removing sulfur compounds without breaking the hydrocarbon chain. Compared to the conventional method, which is in vogue currently, bio-sorptive desulfurization (synergism of adsorption and biodesulfurization) would be a more viable option for futuristic implications. This process aids in the sequestration of sulfur more efficiently from the aromatic compounds present in the fuel.
In the proposed methodology, the isolated suitable nanozymes and microbes such as Pseudomonas, Gordonia sp, Rhodococcus, Bacillus etc., would be immobilised on biopolymer viz. chitosan, chitin, cellulose etc., The synthesized biosorbents would be used for desulfurization of model and commercial fuel. The biosorbents would be tested for their regeneration capacity and recyclability of the cell support in benign solvents.
Batch studies would be carried out by equilibrating a known weight of the biosorbent with varying concentrations of sulfur. For scale-up, a fixed bed flowing system would be used with a controlled flow rate peristaltic pump to move a model fuel sample through the column at room temperature. After the adsorption process, samples of the treated fuels would be tested at various time intervals and the thiophenic compounds (sulfur) would be quantified spectrophotometrically as well as GC-FID and CHNS analysis.
The proposed biosorbent-based materials and method target Ultra Low Sulfur fuel coupled with versatile applications such as sensing and other environmental remediation.
BITS Supervisor
N Rajesh, Senior Professor
RMIT Supervisor
Rajesh Ramanathan, Professor
Other Supervisor BITS
Vidya Rajesh, Professor
Other Supervisor RMIT
Prof. James Tardio
Required discipline background of candidate
| Discipline |
| Biochemistry, Bioengineering, Biomaterials, Biotech, Biomed Eng/Sciences, Bioinformatics |
| Chemistry |
| Environmental Science and Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Photoelectrochemical oxidation of small molecules by Tungstates and Ferrites for enhanced hydrogen generation
PROJECT DESCRIPTION
Renewable energy has received much attention recently as energy demands and environmental issues continue to climb. Solar, wind, and hydropower are cleaner sources of energy that can meet future needs. Photoelectrochemical (PEC) water splitting constitutes a prospective methodology for utilizing solar energy, facilitating its conversion into storable hydrogen (H2). PEC cells efficiently convert light energy into high-energy electrons and holes for chemical reactions without environmental emissions. However, the sluggish water oxidation reaction (OER)attributed to the complex four-electron transfer process, necessitates a high overpotential and exhibits poor kinetics. Therefore, coupling a favorable anodic oxidation reaction to generate value-added products instead of water oxidation can improve the overall PEC efficiency. The plastic waste anode photo-electrooxidation and cathodic hydrogen evolution reaction (HER) system may increase light and electricity efficiency and create high-valued chemicals on both sides. In this project, we aim to convert small organic molecules, particularly those derived from plastic wastes such as polylactic acid, polyethylene glycol terephthalate, polyethylene, polyethylene furanoate to value-added chemicals via photo-oxidation, and at the same time pair this reaction with the HER. We will focus on tungstates and ferrites, which possess advantageous properties: in addition to a desirable optical bandgap, they can show efficient charge-carrier separation and transport which are crucial for maximizing the efficiency of PEC cells. Various tungstate and ferrites will be explored and optimized in composition and morphology to increase optical absorbance and improve charge carrier separation, for example, by synthesizing vertical 2-dimensional nanostructures which provide enhanced light trapping and effective charge transport.
Aim and Methodology:
1. Synthesis of different metal tungstates and ferrites on conducting substrates like FTO or ITO following wet-chemistry techniques, including solvothermal, spin coating, spray coating etc and their characterizations.
2. Study the photoelectrochemical activity of all the developed photoelectrodes in an improved H2 generation process.
BITS Supervisor
Mrinmoyee Basu
RMIT Supervisor
Prof. Enrico Della Gaspera
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
AI/ML-based prediction of surface roughness, fatigue life and coating parameters for additively manufactured metal parts
Additive manufacturing (AM) of polymers, metals, and alloys of high strength and light weight is consistently improving as a viable process for manufacturing complex geometry parts in space, aerospace, automotive, and healthcare applications. In healthcare applications, oral and maxillofacial surgery (OMFS) has revolutionized the possibility of additive manufacturing due to its ability to accurately manufacture the necessary complex geometry Titanium structural elements of the face and jaw-bones. The poor surface finish of the parts made by AM is among the major concerns on which further research is needed, as poor finish affects the part's functionality in terms of fatigue life and corrosion resistance. To correct the surface topography, all the as-built AM metal parts are invariably subjected to either a surface material removal-based finishing or a coating-based finishing process, or both. The coating process may be an off-line post-AM process such as thermal spray coating, PVD, or CVD. The coating may also be achieved using the same AM machine in situ in case of a direct energy deposition (DED) process. Correctly planning and implementing these finishing processes and subsequent fatigue and corrosion resistance requires integration with the AM process parameter data and an intelligent deep-learning engine. Among the various AM process parameters that affect the surface finish and waviness of the part surfaces are (i) build orientation, (ii) laser power setting, (iii) feed rate, (iv) layer thickness, (v) hatch spacing, and (vi) material properties.
In this project, a computational model of the AM process will be developed to predict surface roughness and waviness as functions of the process parameters on a benchmarked part having surfaces of different representative orientations and curvatures. The results of the computational model will be validated and supported by a DOE-selected experimental AM fabrication of specimens and measurement of surface finish and waviness. The data generated will be used to train a suitable AIML model until its predictability is raised to acceptable levels. Then the AIML predictions will be extended to planning surface material removal-based and coating-based finishing process parameters.
BITS Supervisor
Prof. Srinivasa Prakash Regalla, Professor
RMIT Supervisor
Sabu John, Professor
Other Supervisor BITS
Kurra Suresh, Associate Professor
Other Supervisor RMIT
Dr. Maciej Mazur Senior Lecturer
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Engineering, Engineering Physics |
| Materials Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Materials for (photo)electrochemical applications
Generation of H2 from water by (photo)electrochemical water splitting has been considered as a promising sustainable approach and can be a potential alternate to conventional fossil-fuel-based non-renewable energy sources. Despite the continuous efforts in green H2¬ production by photo and electrochemical approaches, the commercial implementation is still in the infancy stage. The anodic oxygen evolution reaction (OER) of water splitting is known to limit the overall efficiency, due to sluggish kinetics of OER. It is noteworthy that around 90% of the electricity is consumed by OER, for instance in electrochemical water splitting approach. Apart from the kinetic limitations of OER, the product formed in OER process has very less economic value.
In this direction, in order to enhance the effectiveness of green fuel production, the present project focus on developing hybrid electrolysis system by integrating hydrogen evolution reaction (HER) with thermodynamically more favorable oxidation reactions, hitherto termed as high-value anodic oxidation reaction (HVAR) as a substitute to OER to maximize energy efficiency and product value.
Therefore, the broad objective is to develop materials for hybrid electrolysis system that produce green H2 with low energy consumption by integrating HER with HVAR (dehydrogenation, oxidation, coupling reactions, etc.) as a substitute to sluggish water oxidation reaction (OER) in traditional (photo)electrochemical water splitting.
BITS Supervisor
Kiran Vankayala
RMIT Supervisor
Prof. Enrico Della Gaspera
Other Supervisor RMIT
Dr Peter Sherrell
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials Science |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Supply Chain Analytics in Retail and Consumer Behavior for E Vehicles.
This project explores the intersection of AI/ML and data analytics in the retail and consumer behavior sectors related to electric vehicles (EVs). By leveraging advanced data science techniques, the study aims to optimize supply chain operations and enhance consumer engagement. The focus is on translating data-driven insights into actionable strategies that support the retail distribution and adoption of EVs. Through predictive analytics, the project assesses consumer preferences, retail trends, and logistical efficiencies, ensuring a resilient and responsive supply chain network.
The project will begin with comprehensive data collection and integration, gathering datasets from retail sales, consumer surveys, and supply chain operations specific to electric vehicles (EVs). This data will be unified into a cohesive platform, enabling thorough analysis. Advanced AI and machine learning techniques, such as clustering, regression analysis, and neural networks, will be applied to identify patterns and predict consumer behavior within the EV market. To optimize logistics and distribution strategies for EV retailers, supply chain simulation models will be employed, testing various scenarios to enhance operational efficiency. A critical aspect of the methodology is the analysis and mitigation of bias in AI models to ensure fair and equitable insights, particularly focusing on gender and demographic representation. Predictive analytics tools will be leveraged to forecast market trends and consumer demands, providing strategic insights for decision-making by retailers and policymakers. Throughout the research, interdisciplinary collaboration will be emphasized, engaging experts from industrial engineering, data science, and consumer psychology to enrich the study's depth and applicability.
BITS Supervisor
Satyendra Kumr Sharma
RMIT Supervisor
Dr Su Nguyen
Other Supervisor BITS
Satyendra Kumr Sharma
Other Supervisor RMIT
Prof. Prem Chhetri, Professor
Required discipline background of candidate
| Discipline |
| Artificial Intelligence |
| Business |
| Business Analytics |
| Data Science, Data Mining, Data Security & Data Engineering |
| MBA (Operations / Supply Chain and Logistics) |
| Public Policy |
|
AI/ML Methods and Applications for Stream Water Quality Modeling
Overview
The Krishna River Basin, one of India's major river systems, faces significant water quality challenges due to industrial effluents, agricultural runoff, and domestic wastewater. Accurate and efficient modeling of stream water quality is essential for sustainable management and pollution control. Traditional water quality models are often limited by data gaps, high computational requirements, and uncertainties in parameter estimation. Artificial Intelligence (AI) and Machine Learning (ML) techniques offer powerful alternatives for predicting and analyzing water quality by learning complex patterns from historical and real-time data.
Aims and Objectives
Develop AI/ML-based predictive models for key water quality parameters (e.g., pH, dissolved oxygen, biochemical oxygen demand, nitrates, heavy metals).
Compare the performance of ML models with traditional statistical and process-based models.
Identify key environmental factors influencing water quality through feature selection techniques.
Implement a real-time water quality monitoring and forecasting system for decision-making.
Methodology
Data Collection & Preprocessing:
Obtain water quality data from government agencies (e.g., CPCB, SPCBs), remote sensing sources, and IoT-based sensors.
Clean and preprocess data using statistical techniques (handling missing values, outlier detection).
Exploratory Data Analysis (EDA) and Feature Engineering:
Apply descriptive statistics and visualization to identify trends and correlations.
Perform dimensionality reduction (PCA, feature selection) to optimize model performance.
Model Development:
Train ML models such as Random Forest, Support Vector Machine, Artificial Neural Networks, and Gradient Boosting.
Use deep learning techniques (LSTMs, CNNs) for temporal and spatial pattern analysis.
Model Validation & Optimization:
Evaluate model accuracy using RMSE, MAE, and R² metrics.
Optimize hyperparameters using grid search and cross-validation.
Deployment & Decision Support System:
Develop a user-friendly dashboard for real-time monitoring and forecasting.
Provide policy recommendations for pollution control and sustainable water management.
By leveraging AI/ML techniques, this project aims to enhance water quality modeling, enabling proactive management strategies for the Krishna River Basin.
BITS Supervisor
Jagadeesh Anmala
RMIT Supervisor
Mohammad Aminpour
Other Supervisor BITS
K. Rajitha
Other Supervisor RMIT
Vikram Garaniya
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
| Environmental Engineering |
| Environmental Science |
| Environmental Science and Engineering |
|
Designing AI-Driven Autonomous Robotic Systems for Enhanced Medical Service Delivery
The need for hospital delivery robots arises from the need for efficient, reliable, and hygienic delivery systems that reduce human involvement and optimize resources. Advanced autonomous robots equipped with AI-driven navigation, sensor fusion, and real-time obstacle avoidance are poised to meet these needs. Unlike the traditional models, our smart robots can adapt to changes in their surroundings, enabling them to move independently through complex hospital spaces.
Current medical robots hold great promise but are hindered by high costs, limited flexibility in dynamic environments, and dependence on structured settings. The proposed solution involves a cost-effective robotic system combining advanced sensor fusion techniques using deep learning, SLAM techniques, and AI-driven navigation. This system features a mobile robot with trays for delivering medications within hospitals and a manipulator for various manipulation tasks like operating lifts, waste disposal, medicine delivery, and patient monitoring tasks. Additionally, integrated voice assistants provide guidance, alerts, and patient support. Designed for autonomous operation in dynamic environments, this innovative approach reduces infrastructure demands and training requirements while enhancing the adaptability and efficiency of healthcare logistics and services.
Objectives and timeline for the proposed work include the following:
1 Create a prototype of delivery robots specifically designed for transporting drugs, and medical supplies within Dubai hospitals
2 Implement sensor fusion and SLAM techniques using IMU, LiDAR, and depth cameras for precise navigation in dynamic hospital environments.
3 Establish key performance metrics including Delivery time, Route optimization efficiency, Collision Avoidance Rate, Energy Consumption, and Localization Accuracy.
4 Integrate deep learning and reinforcement learning algorithms into the robots for dynamic path planning and decision-making to enhance real-time adaptability.
5 Conduct simulations and real-world tests to validate the robots' performance against hospital logistics needs, ensuring safety, reliability, and efficiency.
References:
Alejandro Cruces et al. [2024], Socially Assistive Robots in Smart Environments to Attend Elderly People—A Survey, https://doi.org/10.3390/app14125287
Luigi Tagliavini et al. [2023], D.O.T. PAQUITOP, an Autonomous Mobile Manipulator for Hospital Assistance
BITS Supervisor
Prof.R. Karthikeyan
RMIT Supervisor
Prof. Hamid Khayyam
Other Supervisor BITS
Dr.V.Kalaichelvi, Professor
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
AI-Enabled Underwater Optical Integrated Sensing and Communication
Underwater communication is critical for advancing ocean exploration, maritime surveillance, climate change studies, and national security. While covering 70% of the Earth's surface, the underwater environment remains one of the least understood domains. This knowledge gap limits our ability to expand scientific frontiers or explore underwater resources, and addressing it requires robust communications capable of supporting data-intensive underwater activities.
Underwater optical wireless communication (UOWC) has emerged as a promising solution, offering broad bandwidth and fast data transmission with relatively low attenuation. It solves the inherent limitations of low bandwidth, slow data rates (typically tens of kilobits per second), and significant transmission latency due to the slow propagation speed of sound in current acoustic-based underwater communication methods (e.g., sonars). It also addresses the severe signal attenuation issue in alternative microwave-based underwater approaches. Therefore, UOWC is highly attractive to meet the growing demands for real-time data exchange in autonomous underwater vehicles (AUVs), wireless sensor networks, and submarine operations.
However, current UOWC systems primarily rely on line-of-sight (LOS) links. This reliance makes UOWC vulnerable to complex and dynamic underwater environments where physical obstructions from suspended particles, marine life and environmental feature (e.g., reefs) are inevitable, and thus, significantly limits real-world applicability.
In this project we aim to leverage machine learning (ML) and investigate a novel high-speed and robust non-line-of-sight (NLOS) UOWC system to solve the fundamental LOS limit and achieve real-time data transmission between underwater platforms in obstructed and dynamic underwater environments even when sources are invisible. In particular, this project will focus on seamlessly integrating ML image processing-based situation awareness with optical-based data communication using optical camera-based receivers for optical integrated sensing and communication (O-ISAC). AI-based approaches will be studied for simultaneous image processing/situation awareness and wireless communication data extraction.
BITS Supervisor
Nitin Sharma Associate Professor
RMIT Supervisor
Ke Wang, Associate Professor and Deputy Head of Department - R&I
Other Supervisor RMIT
Akram Hourani, Professor
Required discipline background of candidate
| Discipline |
| Computer Vision, Image Processing, Virtual Reality |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Networks and Communications, Wireless Comms, Telecommunications |
| Neural Networks |
|
MXene mediated bandgap-engineered all-solid-state Z-Scheme heterojunctions: photoelectrocatalysts for green hydrogen production at low bias and solar light
Main Objective:
Development of highly efficient photoelectrocatalyst for green hydrogen production under low bias and solar light exposure.
(1) Design of nanostructured all-solid-state Z-scheme heterojunctions by combining a 2-D semiconductor with another semiconductor nanoparticle.
(2) Bandgap engineering of these Z-scheme heterojunctions by judiciously choosing semiconductors with suitable band positions (conduction band and valence band).
(3) Evaluation of the photoelectrocatalytic performances of the synthesized heterojunctions for green hydrogen production via water splitting under low bias and visible light exposure.
Methodology
Task -1 Development of synthesis methodologies to create suitable heterojunctions by decorating the semiconductor nanoparticles on the surface and within the layered structures of the 2-D semiconductors ((i.e., Potassium poly(heptazineimide) (K-PHI)) and placing the nanosheets of exfoliated MXenes at the interface between the two semiconductors.
Task 2: Tuning the band gap, and band positions (CB and VB) by controlling the nature, compositions, and microstructures of the semiconducting nanomaterials.
Task 3: Structural characterizations of the synthesized materials by using XRD, XPS, FESEM, HRTEM, Raman Spectroscopy, FTIR, UV-Vis DRS, etc.
Task 4: Investigations on the photocatalytic efficiency of synthesized heterojunctions towards the Hydrogen evolution reaction (HER) by determining overpotential, onset potential, Tafel slope, Turnover Frequency, Mass activity, electrochemically active surface area, roughness factor, specific activity, stability of the electrocatalyst, etc.
Task 5: DFT calculations to understand the electronic structures of the heterojunctions and their influence on the performance of the catalyst.
Task 6: Explore the efficacy of green hydrogen production from seawater via photoelectrocatalysis using the synthesized catalysts.
BITS Supervisor
Dr NARENDRA NATH GHOSH and Professor
RMIT Supervisor
Dr Derek Hao and Vice Chancellor’s Postdoctoral Fellowship
Required discipline background of candidate
| Discipline |
| Chemistry or Chemical Sciences |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| PHYSICS |
|
Machine Learning and Quantum Computing for Real-Time Power System Stability Analysis and Visualisation
The increasing penetration of renewable energy sources and power electronic converters in modern power systems introduces significant challenges in ensuring system stability. Traditional methods for transient and dynamic stability analysis rely on computationally intensive time-domain simulations, which are not well-suited for real-time applications. This research aims to develop a novel framework that integrates advanced machine learning techniques and quantum computing approaches to enable real-time monitoring, stability assessment, and decision support for power systems.
2. Aims and Objectives
This research focuses on the development of machine learning-based approaches, including deep learning and graph neural networks (GNNs), for transient and multi-stability risk assessment in power grids. Additionally, the project explores quantum computing strategies for enhancing computational efficiency in real-time stability analysis.
The key objectives of this study are:
i. To develop a real-time power system monitoring framework using machine learning techniques for transient and dynamic stability assessment.
ii. To design machine learning models for analysing interactions between power electronic converter-based resources in power grids.
iii. To explore quantum computing algorithms for improving the efficiency of stability assessments and enhancing predictive accuracy.
3. Methodology
This research will employ a hybrid approach that integrates machine learning and quantum computing techniques:
i. Machine Learning for Power System Stability
ii. Utilise cascaded convolutional neural networks (CNNs) for fast transient stability batch assessment.
iii. Apply graph neural networks (GNNs) to assess multi-stability risks in real-time power systems.
iv Develop machine learning models to analyse inverter-based resource interactions.
v. Quantum Computing for Stability Analysis
vi. Investigate quantum-assisted optimisation techniques for reducing computational complexity.
vii. Implement quantum-enhanced machine learning models for real-time power system risk assessment.
viii. Simulation and Validation
ix. Evaluate the developed models using real-time simulation tools and benchmark datasets (e.g., IEEE 39-bus and Polish 2383-bus systems).
x. Compare the proposed approach with traditional methods in terms of accuracy, computational efficiency, and robustness.
BITS Supervisor
Dr. Neha Tak
RMIT Supervisor
Assoc. Prof. Lasantha Meegahapola
Other Supervisor BITS
Pratyush Chakraborty
Other Supervisor RMIT
Malka N. Halgamuge
Required discipline background of candidate
| Discipline |
| Computer Science and Engineering/Computer Engineering |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Neural Networks |
|
Cyber Security Readiness of Manufacturing Firms in India
India which is known for a rapid expansion of a digital economy is being lacked behind in terms of cyber security and has become one of the primary targets (i.e. ranked 6th) for cyber security attacks (Sectrio, 2024). It has been estimated the loss for large enterprises to be 10.3 million USD and the loss for mid-sized firms to be 11,000 USD annually in India (PYMNTS, 2018). Even though the Indian government has been attempting to address this issue by enacting new laws (e.g. Information Technology Act 2000 and Personal Data Protection Bill 2019), this issue has no sign to slow down or decrease. The Indian Computer Emergency Response Team (CERT-In) reported that the numbers of cyber security incidents have increased from 552 cases in 2006 to 1.5 million cases in 2023 (CERT-In, 2006; CERT-In, 2023). Based on the report published by Kroll (2024), the manufacturing sector is ranked second impacted by ransomware despite their effort in prioritising on this issue more than average across all other sectors. A similar report published by Sectrio (2024) also confirmed that the volume of cyber security attacks on the manufacturing sector is increasing every year, and this sector is ranked 3rd as the popular target and that the money paid by the victim businesses to recover the data held by ransomware was approximately 53,001 USD/GB. Among those manufacturing firms, ESET (2024) has identified that small and medium-sized enterprises (SMEs) are the most vulnerable due to a lack of employee cyber awareness (45 per cent) and inadequate security measures (44 per cent). To overcome this issue, ASPIA (2023) has proposed that several factors should be considered including regulatory frameworks, cyber security education and skill development, public–private partnership, new technology adoption, cyber security awareness, critical infrastructure protection, and international cooperation.
This research proposes to explore the current cyber security situation in SMEs in India. A mixed-method approach is expected to be used to determine the factors that inhibit the improvement of cyber security infrastructure, awareness, knowledge, and skills among SMEs.
BITS Supervisor
RAJESH MATAI
RMIT Supervisor
Siddhi Pittayachawan
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Computer Science and Information Systems |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Information Technology |
|
Obstacle-Aware Object-tracking using Unmanned Aerial Vehicles (UAVs)
This collaborative PhD project between BITS Pilani and RMIT University aims to develop an advanced, obstacle-aware object-tracking system using Unmanned Aerial Vehicles (UAVs). The project tackles the challenge of robustly tracking moving targets in complex urban environments where obstacles (buildings, trees, vehicles) frequently obscure the target from the UAV's view. Object tracking in UAVs in an obstacle-free environment is a well-studied topic. However, object tracking using UAVs in such a challenging environment has not been studied enough and lacks satisfactory solutions.
Some potential applications of this project include surveillance and policing, especially from a Smart Cities perspective, infrastructure inspection, healthcare supplies and other delivery services, search and rescue operations, etc.
The system's core will be a network of UAVs with onboard computer vision, primarily using algorithms like YOLO. These will be optimised for real-time performance on embedded platforms like Google Coral TPUs. Localised processing minimises latency, enabling rapid response to target and obstacle movements. These algorithms will also optimize energy consumption as they are targetted for UAVs, which are resource-contained platforms with limited battery capacity.
A key innovation is developing intelligent algorithms to handle occlusion and dynamic environments. This involves:
Predictive Obstacle Avoidance: The system reacts to and predicts obstacle and target movements based on trajectories and context. This allows UAVs to adjust flight paths proactively.
Multi-UAV Cooperative Tracking: Multiple UAVs will track the same target or a set of targets, providing redundancy. A distributed target registration and data fusion algorithm combines information, ensuring correct identification even with temporary obscuration. Robust communication and synchronisation are crucial.
Hybrid Onboard/Cloud Processing: Most image processing will be onboard, but cloud computing will be used for tasks like long-term trajectory analysis. Algorithms will be designed to be resilient to communication delays.
Adaptive Tracking Strategies: The system will include adaptive algorithms that modify tracking behaviours in real-time, switching between algorithms based on occlusion, target speed, and obstacle density. It will learn and refine these strategies, improving performance.
The goal is a reliable and adaptable UAV-based tracking system for challenging urban environments.
BITS Supervisor
Sai Sesha Chalapathi Gattupalli
RMIT Supervisor
Chi-Tsun (Ben) Cheng
Other Supervisor RMIT
Dr Ehsan Asadi
Required discipline background of candidate
| Discipline |
| Computer Vision, Image Processing, Virtual Reality |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
The impact of digital transformation on firm innovation and performance using AI ML in Accounting and Finance
The use of digital technologies in firms is transforming businesses globally. The increasing adoption of these digital technologies, such as AI-powered decision-support systems, data analytics, and cloud computing, can improve organisational innovation, enhance customer experience, drive performance improvements, and strengthen risk management frameworks. Adopting digital technologies can also have negative impacts, such as increased complexity, data overload, data security risks, and resistance to change by employees, to name a few. However, despite the growing application of digital technologies in business functions, their specific impact on firm outcomes, such as firm innovation and performance, remains underexplored in academic literature. The increasing complexity of decision-making with digital technologies necessitates an in-depth examination of how digital transformation shapes financial strategy and organisational performance. This study addresses the research problem by investigating how digital transformation influences firm outcomes. Digital transformation might impact firm value differently across industries, especially those handling sensitive data, like healthcare and banking industries. These industries face heightened cybersecurity risks, as cyberattacks targeting sensitive data (medical records, financial information) can result in financial losses, reputational damage, and regulatory penalties. Hence, we would like to analyse the impact of digital transformation on firm outcomes and bring out the difference in impact across industries. The objectives of the project are threefold. First, it aims to develop a measure of digital transformation using textual analysis of annual reports of listed firms in various industries. Second, it assesses how digital transformation impacts firm outcomes such as innovation and performance. Third, the study investigates how the impact is different across industries. The methodology adopted will be AI and ML techniques for our study. AI-powered LLMs leveraging techniques like Natural Language processing will be used to develop the digital transformation score for our listed firms. LLM analysis will be performed on the annual reports of listed firms. We will be using secondary data sources to determine the financial characteristics of listed firms. Supervised machine learning approaches and financial econometrics will be used to analyse the impact of digital transformation on firm outcomes.
BITS Supervisor
Prof. Nivedita Sinha
RMIT Supervisor
Associate Professor Tarek Rana
Other Supervisor BITS
Prof. Aruna Malapati
Required discipline background of candidate
| Discipline |
| Accounting |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Data Science |
| Finance |
|
Design and Development of Plasmonic Metasurfaces for Enhanced Sensing and Solar Energy Harvesting Applications
Plasmonic metasurfaces are artificial materials engineered to possess specific optical characteristics that are absent from materials that arise naturally. The subwavelength structures that make up these metasurfaces are usually able to control light by means of plasmonic resonances at the metal-dielectric interface. Because of their intriguing characteristics, including improved light-matter interactions, light confinement, and nanoscale electromagnetic field control, plasmonic metasurfaces hold great promise for various sensing and solar energy harvesting applications. Plasmonic metasurfaces can facilitate the sensitive detection of gases, biomolecules, and environmental contaminants. High sensitivity and selectivity for detecting extremely low concentrations of target analytes can result from their capacity to amplify signals via localized surface plasmon resonance (LSPR). These metasurfaces also have the potential to increase solar cell efficiency through improved light absorption, which would allow for more efficient light trapping and energy conversion in solar energy harvesting devices such as perovskite and organic solar cells.
Objectives:
This proposal aims to develop novel plasmonic metasurfaces that can be optimized for both sensing and solar energy applications. The primary objectives are:
1. To design and fabricate highly sensitive plasmonic metasurfaces for biosensing applications by utilizing surface plasmon resonance (SPR) and LSPR effects.
2. To develop plasmonic metasurfaces for solar cell applications, improving light absorption and photon-to-electron conversion efficiency.
3. To explore the dual functionality of metasurfaces that can be optimized for both sensing and energy harvesting devices.
4. To characterize the fabricated metasurfaces in terms of their optical and structural properties and evaluate their performance in real-world sensing and solar energy applications.
This research proposal aims to improve our knowledge and utilization of plasmonic metasurfaces in two high-impact fields: solar energy harvesting and sensing. The project intends to offer creative solutions for boosting environmental monitoring and increasing the effectiveness of renewable energy systems by fusing the advantages of both domains.
BITS Supervisor
Pankaj Arora
RMIT Supervisor
Md Ataur Rahman
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Materials Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Development of Engineered Bio-nanocomposites for Packaging Application: An Indo-Australian Study
Bio based reinforcement materials have also attracted significant attention during the past decade, mainly due to ecological and climatic factors along with their superior strength, low density, non-abrasiveness, low cost, and biodegradable properties. Therefore, the development of high performance flame retardant fully biodegradable bio composite product, with optimized thermos-mechanical properties is an important and urgent task and an important step forward towards sustainability. Recently, interest has grown in the use of nanoscale fillers because of their distinctive advantages, such as dramatic improvement in mechanical properties with low filler content, to produce new value-added products to a great extent interact with the polymer, further enhancing the effectiveness of the reinforcement. However, in most cases, the nanofillers are either expensive or the structure-property correlations are poorly understood. Against these backgrounds, there is a critical need to develop bio-nanocomposite materials with a detailed understanding of their structure-property correlations and this proposal makes an attempt to fill that lacuna. This Proposal will aims : • To develop biodegradable bio-nanocomposites by using engineered natural fibres, biodegradable polymer matrix, suitable additives and compatibilising agents. • To study the effects of various materials and process parameters (such as extrusion variables, coupling agents, equivalence ratio, moisture content, etc.) on the performance (mechanical, thermal, thermos-mechanical properties) of developed bio composites. • Use of fractography, micro-structural characterizations to understand the fracture behavior of developed bio composites. • To study and enhance flame retardant properties of engineered bio-nanocomposites. • Finite element modelling of materials to understand the fracture behavior of developed bio composites under different boundary condition and different loading condition
BITS Supervisor
SHARAD SHRIVASTAVA ASSOCIATE PROFESSOR
RMIT Supervisor
Srinivas Nunna
Other Supervisor BITS
Arun Kumar Jalan
Other Supervisor RMIT
Raj Ladani
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Adaptive Building Reuse, a multicriteria analysis tool for re-designing floorplans, layouts and space utilisation
With modern times, there is a gradual change in the housing requirements because of multiple factors as follows:
• Joint families are getting replaced by nuclear families,
• Many families have one or no children (earlier there used to be 2 or more children)
• Office spaces and study rooms are essential which were not present in earlier designs.
Hence, existing floorplans need to be re-designed while meeting the modern requirements in such a way that they remain adaptive for a longer period. Further, adaptive reuse of buildings is paramount if need to reduce the carbon footprint of new construction work. Other imperatives not only for increasing building life-cycle but also for revaluing heritage architecture.
Reconfiguring the space needs and requirements of existing buildings is challenging. Various constrains make it difficult to reutilising spaces, there include: quality and space standards, disable access, safety compliance amongst other limitations to re-utilising space. Hence, software applications that assist with the spatial and configuration analyses are highly relevant to the better intervention of heritage site and existing buildings.
In this project, we aim to develop graph algorithms, supported by optimization tools, to regenerate architecturally acceptable building layouts. The methodology will cover the following aspects:
1. Extracting the following data from existing buildings
• Plot boundary
• Presence of fixed spaces such as stairs and columns
2. Finalizing the list of inputs
To redesign the layout, the following input are required:
• Bubble Diagram: A structured representation of spatial relationships, specifying the number of rooms, required adjacencies and non-adjacencies, and the distinction between interior and exterior rooms.
• Room Sizes and Proportions
• Cardinal Orientation (Sunlight Optimization)
• Circulation and Access
3. Designing of algorithms
Next is to develop graph algorithms and optimization tools for placing the given rooms within the plot boundary while minimizing the waste space and satisfying the given adjacencies and dimensional constraints.
4. Validation and Iterative Refinement
To enhance the practical applicability of the generated layouts, we will conduct a validation phase involving expert feedback from architects.
BITS Supervisor
A/Prof Krishnendra Shekhawat
RMIT Supervisor
Associate Professor Guillermo Aranda-Mena
Required discipline background of candidate
| Discipline |
| Architecture & Built Environment |
| Computer Science |
| Construction Eng/Management and Materials |
| Design, Design Engineering, Sustainable Design |
| Mathematical Science |
|
Government Health Policies and their Impact on Maternal and Child Health Services and Health Outcomes in India
As one of the most populous countries in the world, India faces significant challenges related to maternal and child health (World Bank, 2020). Although a major component of its healthcare budget is allocated towards improving child and maternal health, India has an extensive private healthcare sector which caters to almost 80% of outpatient services (Rao, Rao, Kumar, et al., 2011; Balasubramaniam, Bartlett, Yadav, et al., 2011). It is important in this context to understand how far public health infrastructure alleviates the economic burden of health among the populace. Further, the success of public health depends on the administrative and logistical capability of other infrastructures, failing which the program may be ineffectual (Ghosh, Kochar, 2017).
The proposed study intends to use the National Sample Survey Organization (NSSO), National Family Health Survey (NFHS) and other government issued databases to analyze the impact of health programs and expenditures on maternal and child health outcomes in India. Over the years, a suite of health schemes has been implemented at both national and state levels. As part of the “Vikasit Bharat” (Developed India) initiative, the government has launched various health programs and progressively increased health expenditure, with the goal of improving maternal and children health and reducing inequalities across states. The National Health Mission (NHM) was launched in India in 2005 with a view to improve health conditions in India and with a special focus on mother and children health. In addition to national initiatives, various state-level schemes have also been implemented to enhance public health conditions. Another key cornerstone of SDG3 is Universal Healthcare Coverage (UHC) which seeks to provide universal access to affordable, high-quality healthcare. The Ayushman Bharat scheme is a central government scheme introduced in 2018, to help address health inequities in the country. Although the scheme is broad in coverage it specifically includes pregnant women and maternity-related services. The impact of this maternal health specific scheme, however, remains unknown.
With a combination of central and state-level schemes in place, aimed at improving maternal health in India, it is critical to assess the effects of healthcare expenditure and government programs on maternal and child health, including in the postpartum period.
BITS Supervisor
Archana Srivastava
RMIT Supervisor
Preety Pratima Srivastava
Required discipline background of candidate
| Discipline |
| Economics |
| Social Sciences, Sociology |
|
Design and Optimization of High-Frequency Inverters for Efficient Underwater Wireless Charging of Unmanned Underwater Vehicles
Motivation:
Unmanned Underwater Vehicles (UUVs) play a crucial role in deep-sea exploration, including early detection of natural disasters, monitoring of marine resources, search and salvage operations, and defense applications. A wireless power charging station, equipped with high-frequency converters and rectifiers, can significantly extend the operational range of UUVs, enabling uninterrupted deep-sea research and missions.
Objectives:
OB1: Development of an Efficient Tx-Rx Coil Module
Design and optimization of a transmitter (Tx) and receiver (Rx) coil module to enhance wireless power transfer (WPT) efficiency.
OB2: Material Selection for Coil Design
Establishing a screening procedure to identify the most suitable materials resistant to corrosion due to underwater salinity, pressure, and temperature fluctuations.
OB3: Design and Fabrication of a High-Frequency Inverter
Developing an efficient power source on the Tx side to ensure stable and high-power transmission.
OB4: Development of an Efficient Rectification Network
Designing and fabricating a rectification network at the Rx end to optimize power conversion.
OB5: Underwater Performance Testing
Evaluating the performance and durability of various components under underwater conditions to ensure reliability.
Methodology:
The proposed research will be conducted in four key stages:
Mathematical Optimization: Utilizing electromagnetic theory and computational tools such as MATLAB to model and optimize Tx-Rx coil configurations.
Simulation-Based Validation: Employing high-performance EM simulation software (e.g., ANSYS HFSS, ANSYS Maxwell, MICROWAVE CST Studio) to validate analytical findings.
High-Frequency Inverter and Rectifier Design: Designing, simulating, and fabricating high-frequency inverters and rectifiers to enhance power
transmission efficiency.
Underwater Performance Testing: Implementing and testing a prototype system to measure critical performance parameters in
underwater conditions.
BITS Supervisor
Ananth Bharadwaj Madduluri
RMIT Supervisor
Prof. Hamid Khayyam
Other Supervisor BITS
Dr. Sunil Thomas
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
|
Efflux pump inhibitor enhanced antimicrobial peptide-based nanozyme for AMR reversal
Summary: Antimicrobial resistance (AMR) poses a significant threat to global health, often driven by bacterial efflux pumps that expel antibiotics, reducing their efficacy. This proposal explores a novel strategy to combat AMR by combining an efflux pump inhibitor (EPI) with an antimicrobial peptide-based nanozyme. The nanozyme enhances bacterial killing through catalytic activity while the EPI prevents drug expulsion, ensuring higher intracellular drug retention. This synergistic approach aims to restore antibiotic susceptibility and improve therapeutic outcomes against resistant pathogens. By integrating nanotechnology and biochemical inhibition, this platform offers a promising alternative to conventional antibiotics, potentially overcoming resistance mechanisms and enhancing treatment efficacy. The findings could pave the way for innovative antimicrobial strategies to tackle multidrug-resistant bacterial infections.
Aims:
1) To develop and characterize the antimicrobial peptide-based nanozyme (BITS-9 months)
2) To evaluate the synergistic effect of the Efflux pump inhibitor and nanozyme (RMIT-12 months)
3) To assess the mechanism and potential for AMR reversal (BITS-12 months)
Methodology:
1. Development and characterization of antimicrobial peptide-based nanozyme for stability, catalytic activity and cytotoxicity.
2. Evaluation of the synergistic efficacy of Efflux pump inhibitor and nanozyme and assessing their therapeutic potential in vitro using MIC/MBC assays.
3. Investigation of the mechanism and potential of EPI-AMP based nanozyme for AMR reversal through RT-qPCR, RNA sequencing, passaging and proteomics.
BITS Supervisor
Professor Jayati Ray Dutta
RMIT Supervisor
A/Prof. Yichao Wang
Other Supervisor BITS
Ramakrishnan Ganesan
Other Supervisor RMIT
Professor Ravi Shukla
Required discipline background of candidate
| Discipline |
| Biotechnology |
| Health, Digital Health |
| Materials Chemistry |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Monolithic Integration of Ga2O3 and GaN on Sapphire Platform for UV-C light source and detector
Ultraviolet-C (UV-C) radiation are commonly utilized in air purification from harmful chemicals, water disinfection from bactericidal effects, treating localised infections, and killing virus (eg. COVID 19). However, excessive exposure to UV-C radiation can cause severe harm to the environment and humans leading to the need of meticulous monitoring of UV-C radiation level using UV-C or solar-blind photodetector. Ultra-wide bandgap semiconductors such as gallium oxide (Ga2O3) have active optoelectronics performance in deep-UV range mainly as photodetection. Due to their intrinsic properties, Ga2O3 is ideal for high power electronics and high temperatures with comparatively small device size and weight unlike most conventional electronic and optoelectronic materials that needs bigger size to operate in such conditions. Secondly, III-nitrides such as gallium nitride (GaN), aluminium nitride (AlN), and their solid solutions, are currently leading wide bandgap semiconductors for use in UV optoelectronics and power electronics. In this project, we propose a marriage between Ga2O3 and GaN to unfold an innovative device having application in deep-UV range for sanitisation and disinfection. The aim of this project is to achieve monolithic integration of Ga2O3 and GaN on a single-chip where Ga2O3 will act as UV-C photodetector and GaN as UV-C LED. The project will be implemented in 3 phases. In the first phase, three device designs will be simulated to understand and predict comparative performance. Simultaneously, the PhD candidate will undertake training and induction related to material characterization and fabrication. In the second phase, material synthesis, characterization, device fabrication, and optoelectronic testing will be conducted. In the third phase, taking feedback from the first set of experiments modifications in the designs and implementation methodology will be adopted for efficient operations. At the key milestones, the focus will be on relevant publications and securing intellectual property where relevant. The project will undertake fundamental research with focus on a proof-of-concept device that can generate UV-C radiation while continuously monitoring radiation level with integrated UV-C detector in a single compact device. This research will address the need of safety in santitisation and disinfection using UV-C radiation with strong prospects for translation.
BITS Supervisor
Professor RAHUL KUMAR
RMIT Supervisor
Shruti Nirantar, Dr
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Materials Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Investigation of covalent and noncovalent interactions of Metal-Organic Frameworks/MXenes Hybrid Nanomaterials with implementation of machine learning for energy storage applications
Metal-organic frameworks (MOFs) are a class of organic-inorganic hybrid materials that have attracted significant attention due to their highly porous structure, versatile physicochemical properties, active metal sites, and wide range of applications for gas storage and separation, catalysis, and energy storage and conversion. MXene materials have garnered significant attention among material scientists, thanks to their diverse structural motifs, rich surface chemistry, and intriguing physicochemical properties. Due to their chemical synthesis, MXene materials can be processed in solution, allowing for tunable surface chemistry. While individual MXene materials possess impressive specific properties, constructing 2D hybrid assemblies with MOF constituents may be necessary to achieve better control over properties according to application requirements. 2D MXenes have been integrated with porous metal-organic frameworks (MOFs) to enhance properties such as stability, conductivity, and catalytic activity. Furthermore, this combination is advantageous for MXenes because the intercalation of MOFs between MXene nanosheets prevents the restacking of the sheets, which is a significant challenge associated with MXenes. This process improves their properties like overall conductivity, durability, and stability for a range of applications. In this work, we aim to propose i) Design of different new two-dimensional (2D) MOFs/MXene hybrid nanomaterials, ii) Investigation of structural, electronic, adsorption, and diffusion properties of newly developed hybrid nanomaterials, and iii) Model the Li, K, and Na atom and hybrid nanomaterials to understand the solid-solid interaction, intercalation reaction mechanism, and behavior of the interface between cathode and newly designed heterostructures and identify Vander Waals interaction and the optimal configuration leading to the maximum conductivity and high energy density. All our calculations will be carried out using density functional theory (DFT) as implemented in Vienna ab initio simulation package (VASP) or Gaussian software with implementation of Machine learning. The ion-electron interactions will be described by proper electron exchange-correlation functional.
BITS Supervisor
PARAMITA HALDAR
RMIT Supervisor
Dr. Ravichandar Babarao
Other Supervisor RMIT
Dr. Tu Le
Required discipline background of candidate
| Discipline |
| Chemical Engineering |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials Science |
| PHYSICS |
|
Intelligent Traffic optimization algorithms for universal homogeneous network performance monitoring
This research focuses on developing AI-driven algorithms for traffic optimization in universal homogeneous network performance monitoring, applicable to both fixed and wireless networks. The project aims to discover innovative AI-based approaches to reduce and optimize network traffic, including intelligent aggregation at the network edge. Homogeneous networks are complex, multi-layered systems that leverage technologies such as network slicing, traffic compression, and multi-path transit. To address the need for an advanced performance monitoring solution that provides a holistic network view, this research will integrate machine learning (ML) and deep learning (DL) techniques for predictive analytics, anomaly detection, and adaptive traffic management. AI models will be developed for real-time traffic classification, congestion forecasting, and dynamic resource allocation, enabling enhanced Quality of Service (QoS) and energy-efficient operations.
The research methodology includes designing a scalable AI-driven framework and simulation model for algorithm testing. Various access network technologies will be incorporated to assess algorithm adaptability across different environments. A key objective is to identify AI-powered traffic optimization techniques that can be seamlessly integrated into heterogeneous networks, forming part of a unified, self-optimizing network management solution.
BITS Supervisor
Dr Nikumani Choudhury
RMIT Supervisor
Associate Professor Mark Gregory
Required discipline background of candidate
| Discipline |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Information Technology |
| Networks and Communications, Wireless Comms, Telecommunications |
|
Wetland plastisphere as a novel biotope
Ubiquitous plastic pollution is a planetary problem. Wetlands (natural or constructed) can act sink of these problem. However, plastic within wetlands can generate a novel biotope called "wetland plastisphere". Wetland plastisphere that refers to the community of organisms that colonise plastic debris, represents a new biotic layer that warrants investigation. This new biotope is creating dynamic habitats that differ significantly from their natural counterparts. Certain microbes may break down plastics, while others may contribute to wetland nutrient cycling. Research into the wetland plastisphere is crucial for understanding the broader implications of plastic pollution on wetland biogeochemistry, nutrient cycling, microbial activity, and overall ecosystem functioning. It also raises important questions about how these biotope function and how they will respond to ongoing environmental changes. As plastic waste continues to accumulate in wetland areas, studying these unique biotopes may offer insights into potential remediation strategies and the resilience of ecosystems in the face of pollution. Overall, the project will investigate the composition and diversity of microbial communities in the wetland plastisphere and their role in nutrient cycling; evaluate how the presence of plastics in wetlands affects biogeochemical processes such as carbon, nitrogen, and phosphorus cycling; and provide recommendations for managing plastic pollution and enhancing biogeochemical functions in wetland ecosystems.
Apart from regular protocols of wetland research, this project will leverage a wide range of microbial and molecular techniques/approaches including multi-omics (i.e. Genomics, Transcriptomics, Metabolomics, etc) to gain insights of wetland plastisphere and their functions.
BITS Supervisor
Srikanth Mutnuri
RMIT Supervisor
Tanveer Adyel
Required discipline background of candidate
| Discipline |
| Biotechnology |
| Environmental Engineering |
| Environmental Science |
|
Exploring second life applications and recycling for EV batteries using AI
Rapid adoption of electric vehicles (EVs) globally has shown a remarkable reduction in tail pipe emissions. However, from a sustainability and circularity perspective, there are significant roadblocks ahead in terms of usage of the EV batteries for second life applications and beyond. Additionally, recycling of critical raw materials (CRM) used in batteries with LFP/NMC chemistries such as Li, Co, Ni etc. needs major attention; else these materials may result in landfill/seawater creating environmental toxicity and health hazard for humans and animals. To create a pathway for second life usage of EV batteries for stationary storage application and subsequently recycling of these batteries using sustainable methods, this project aims to leverage AI-based framework for building an integrated system for techno-economic feasibility and circular economy of EV batteries for its usage in second life applications and subsequently greener technologies for recycling of CRMs.
The research addresses the question: Can EV batteries be sustainably managed for second life applications and recovering critical raw materials using AI?
Commencing with a detailed literature survey on existing techniques for testing and validation of EV batteries for second life applications, the project will consider the R-ladder of circularity to explore different techniques and their feasibility for second life application of batteries. Techno-economic studies for characterization of EV battery packs for identifying suitability for second life applications will be carried out. AI-integrated solutions will be developed to enhance the cell sorting based on state-of-health and internal resistance of batteries and their rapid integration into usable battery packs for second life applications. Furthermore, suitable greener technologies for recycling of CRMs will be assessed and a pathway for reuse of CRMs for making fresh batteries will be developed.
Following this, an AI-driven framework will be developed forming the crux of this project. This shall include the reusability of EV batteries for second life applications and its recycling of CRMs. This framework will help in real-time identification of cells usability till its end-of-life and help the EV industry to optimise the usage of battery packs and its reusability, therefore, gaining additional benefits in terms of sustainability, circular economy, and commercial viability.
BITS Supervisor
Dr. Tribeni Roy
RMIT Supervisor
Prof. Usha Iyer-Raniga
Required discipline background of candidate
| Discipline |
| Data Science, Data Mining, Data Security & Data Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| MSc (with major subject Optimization) / MSc in Economics |
|
Development and Analysis of ß-Gallium Oxide-based Junction Barrier Schottky Diodes (JBSD)
1. State of the Art:
ß-Gallium Oxide (ß-Ga2O3)-based devices have gained significant interest for next-generation power electronics due to their superior material properties. With a high bandgap (4.4 – 4.9 eV) compared to Gallium Nitride (GaN) (3.4 eV) and Silicon Carbide (SiC) (3.2 eV), Ga2O3 enables a much higher breakdown electric field (8 MV/cm), making it an attractive candidate for power devices. The suitability of a semiconductor for power application is often evaluated using Baliga’s Figure of Merit (BFOM), which considers bandgap, breakdown electric field, and electron mobility. ß-Ga2O3 exhibits a BFOM of around 3000, which is four times higher than GaN and ten times higher than SiC, making it a strong candidate for high-power electronic applications.
2. Methodology
*Device design and fabrication:
•Ga2O3 will be grown via Low-Pressure Chemical Vapor Deposition (LPCVD) on industry-standard c-plane sapphire substrates. The growth process will utilise a Lindberg tube furnace with a solid gallium source, while oxygen and argon serve as the carrier gases.
•NiO will also be deposited using LPCVD, with deposition conditions optimised for uniformity, crystallinity, and interface quality.
•Ohmic contacts (Ti/Au) and Schottky contacts (Pt or Ni/Au) will be formed using RF magnetron sputtering.
*Material characterization:
•X-ray Diffraction (XRD) & Raman Spectroscopy: To analyse crystalline quality.
•Atomic Force Microscopy (AFM) & Scanning Electron Microscopy (SEM): For surface morphology, grain structure, and roughness assessment.
•X-ray Photoelectron Spectroscopy (XPS): To investigate chemical states, bonding configurations, and interface quality.
*Electrical characterization:
•Hall effect measurement: To determine carrier mobility, type, and doping concentration.
•Current-Voltage (I-V) measurement: To extract diode performance metrics such as turn-on voltage, leakage current, breakdown voltage (VBR), and on-resistance (Ron).
•Temperature-Dependent measurement: To investigate device performance over a wide temperature range and assess thermal stability.
BITS Supervisor
Apurba Chakraborty
RMIT Supervisor
Dr Hiep Tran
Other Supervisor BITS
Professor RAHUL KUMAR
Other Supervisor RMIT
A/Prof James Partridge
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| Physics, Condensed Matter Physics |
|
2D materials obtained from liquid metals for next generation wearable optoelectronics
This PhD project focuses on the synthesis and characterization of atomically thin semiconductors, dielectrics, and conductors derived from liquid metals, targeting next-generation optoelectronic and flexible device applications. Two-dimensional (2D) materials, including semiconductors, ferroelectrics, and piezoelectrics, offer the potential to revolutionize electronic devices by drastically reducing energy consumption compared to conventional silicon-based technologies. The project will utilize liquid metal-based printing techniques to produce post-transition metal compounds, particularly gallium, indium, and tin-based materials. These self-limiting oxide layers, which naturally form on the surface of liquid metals, can be exfoliated into high-performing nano-layers with tunable properties. The PhD candidate will synthesize and characterize these materials using advanced electron microscopy, optical spectroscopy, and electronic measurements. The project will further integrate these materials into device architectures, employing state-of-the-art lithography techniques, including ion beam, electron beam, and photolithography, to fabricate scalable, high-efficiency electronic and optoelectronic devices. By exploring charge doping and atomic-scale interactions, this research aims to establish a fundamental understanding of these novel materials, paving the way for their application in printed electronics, sensors, and wearable technologies.
BITS Supervisor
Professor RAHUL KUMAR
RMIT Supervisor
Dr Ali Zavabeti
Other Supervisor RMIT
Prof. Torben Daeneke
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Engineering, Engineering Physics |
| Materials Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Development of ML assisted adaptive strategy to control the anomalies and properties during wire arc additive manufacturing of magnesium-based alloy.
This project addresses critical research gaps in the Wire Arc Additive Manufacturing (WAAM) of magnesium alloys, a promising class of biomaterials for orthopedics, cardiology, and other biomedical applications. WAAM, particularly using arc-based processes like GTAW/GMAW, offers significant advantages over other additive manufacturing techniques. Its lower operational and setup costs and wire feedstock (minimizing material waste) make it a highly efficient and cost-effective approach. Magnesium alloys, especially AZ31B, are particularly interesting due to their biocompatibility, biodegradability, and mechanical properties similar to bone. However, realizing the full potential of WAAM-fabricated AZ31B components requires overcoming challenges in achieving consistent mechanical properties due to process-induced anomalies. Current WAAM processes often suffer from surface roughness, inconsistent wall thickness, and variations in single-layer deposition height, leading to unpredictable material behavior. Existing control methods lack the adaptability and real-time responsiveness to address these complexities. This project pioneers the development of AI-driven intelligent control for WAAM, integrating real-time sensor data (e.g., thermal imaging, arc voltage) with advanced computer vision techniques and machine learning algorithms. This closed-loop system will dynamically adjust process parameters (e.g., wire feed rate, arc current, travel speed) to optimize melt pool dynamics and achieve unprecedented control over microstructure (e.g., grain size, phase distribution) and dimensional accuracy. This research aims to enhance mechanical properties, reduce defects, and improve surface finish by targeting specific anomalies like porosity and cracking, bringing WAAM-fabricated magnesium alloys, particularly AZ31B, closer to their full potential. The project's value lies in its potential to revolutionize the production of customized biomedical implants, offering improved performance, reduced costs, and faster turnaround times compared to traditional manufacturing. This research will advance the fundamental understanding of WAAM and establish a foundation for commercialization and industry collaboration, paving the way for wider adoption of magnesium alloys in demanding applications. The project will deliver validated AI models, a demonstrator WAAM system, and comprehensive characterization data.
BITS Supervisor
Ravi Shanker Vidyarthy
RMIT Supervisor
Dr. Maciej Mazur Senior Lecturer
Other Supervisor RMIT
Dr. Tu Le
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Artificial Intelligence |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Eco-Friendly Compostable Electronics for Sustainable Agriculture
The main goal is to create high-performance green electronics using sustainable materials and processes while demonstrating their application in digital and precision agriculture. This field has been chosen as a testbed for evaluating the degradability of the proposed solution, in addition to being a significant area where electronics can have a positive impact.
Project Objectives
1. Development of Sustainable Materials:
o Explore biodegradable materials such as natural polymers (e.g., starch, cellulose, chitin) for substrate and encapsulation.
o Use conductive polymers (e.g., PEDOT:PSS) and common metals (e.g., Cu, Fe, Zn, Ni) to create environmentally friendly electronic tracks.
2. Design of Compostable Sensors:
o Develop pH and bioimpedance sensors using biodegradable materials.
o Implement minimally invasive microneedle-based bioimpedance sensors to assess plant health.
3. Reusable Electronic Interface Module:
o Design low-power, reusable modules for data acquisition and communication.
o Optimize for disassembly and repairability, employing technologies like LoRa, Bluetooth Low Energy (BTLE), or RFID for wireless data transfer.
4. Investigate Degradation Rates:
• Examine the degradation rates of compostable electronics in various soil types and environmental conditions to optimize material selection and design.
Methodology and Work Plan
1. Material Development
o Select biodegradable materials suitable for electronic applications.
o Characterize materials for properties such as conductivity, durability, dielectric behaviour, and biodegradability under controlled conditions.
2. Sensor Fabrication
o Develop multisensory patches combining pH and bioimpedance sensors.
o Utilize scalable printing and deposition techniques to produce environmentally friendly sensors.
3. Reusable Module Design
o Integrate reusable electronics with the developed sensors.
o Design efficient energy management and communication systems for autonomous operation
BITS Supervisor
Sanket Goel
RMIT Supervisor
A/Prof. Yichao Wang
Other Supervisor BITS
Satish Kumar Dubey
Required discipline background of candidate
| Discipline |
| Chemistry |
| Electrical and Electronics Engineering, Power Engineering |
| Materials Science |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Machine Learning-Enhanced Optimization of Photovoltaic-Thermal (PVT) Systems for Green Hydrogen Production
In this proposed research, we prioritise advanced machine learning (ML) methodologies, including artificial neural networks (ANN) and reinforcement learning (RL), to optimise the efficiency of photovoltaic-thermal (PVT) solar collectors integrated with hydrogen production systems. ML models will be developed, trained, and validated using data gathered from carefully controlled experiments designed to study the influence of fluid flow rates and phase change materials (PCM), specifically paraffin wax, on system performance.
Through ANN modeling, we will accurately predict electrical and thermal efficiency, as well as hydrogen production rates, significantly reducing the need for extensive physical experimentation. RL algorithms will be employed to dynamically optimise key operational parameters such as fluid flow rate and temperature management in real-time, enhancing both responsiveness and hydrogen yield under diverse environmental conditions.
In parallel, a physical test rig will be fabricated to provide essential validation data. Water will serve as the primary heat transfer fluid, and paraffin wax will be used as the PCM to enhance thermal storage and stabilise system operations. The hybrid integration of experimental and computational approaches will enable comprehensive performance analysis and optimisation.
BITS Supervisor
Mani Sankar Dasgupta
RMIT Supervisor
Dr. Sara Vahaji
Other Supervisor BITS
Assistant Professor Suvanjan Bhattacharyya
Other Supervisor RMIT
Amirali Khodadadian Gostar
Required discipline background of candidate
| Discipline |
| Computational Fluid Dynamics & Fluid Mechanics, Modelling |
| Computer Science |
| ENGINEERING PHYSICS |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Use of AI in Route Optimization in the Indian Logistics Sector
1. Introduction:
The Indian logistics sector is a crucial component of the country's economy, contributing significantly to trade, commerce, and supply chain efficiency. However, logistical operations in India face challenges such as congestion, unpredictable weather, fuel inefficiencies, and inconsistent route planning. Implementing Artificial Intelligence (AI) for route optimization can enhance efficiency, reduce costs, and improve overall delivery performance.
2. Problem Statement:
India's logistics sector suffers from high transportation costs, inefficient fuel usage, frequent delivery delays, and poor road infrastructure. Traditional route planning methods rely on static maps and outdated information, leading to inefficiencies. AI-driven route optimization can address these challenges by leveraging real-time data and predictive analytics.
3. Objectives:
• Implement AI-based solutions for dynamic route optimization.
• Reduce transportation costs by minimizing fuel consumption.
• Enhance delivery efficiency and reduce delays.
• Improve sustainability by lowering carbon emissions.
• Utilize real-time traffic data and predictive analytics to make informed routing decisions.
4. AI-based Route Optimization Approach:
AI can be integrated into logistics operations using the following methods:
• Machine Learning Algorithms: AI can analyze past delivery data, traffic patterns, and environmental conditions to suggest optimal routes.
• Real-time Traffic Analysis: AI tools process live traffic updates to reroute deliveries dynamically, avoiding congested areas.
• Predictive Analytics: Historical data and AI models help anticipate delays due to weather, road conditions.
• IoT Integration: Smart GPS tracking and IoT sensors can provide real-time fleet monitoring and enhance route planning.
• Autonomous Decision Making: AI can automate routing decisions based on delivery priority, vehicle capacity, and resource availability.
5. Expected Benefits:
• Cost Reduction: AI-powered route optimization can lead to significant fuel savings and low costs.
• Improved Efficiency: AI reduces delivery time by selecting optimal paths.
• Enhanced Customer Satisfaction: Faster and more accurate deliveries improve customer trust.
• Environmental Impact: Reduced fuel consumption leads to lower greenhouse gas emissions.
Conclusion:
AI-driven route optimization can revolutionize the Indian logistics sector by enhancing operational efficiency, reducing costs, and promoting sustainability.
BITS Supervisor
RAJESH MATAI
RMIT Supervisor
Priyabrata Chowdhury
Other Supervisor RMIT
Kwok Hung Lau
Required discipline background of candidate
| Discipline |
| Business Analytics |
| Data Science, Data Mining, Data Security & Data Engineering |
| MBA (Operations / Supply Chain and Logistics) |
| ME (Industrial/Production Engineering) |
|
Design, development, and performance optimization of thermal energy storage battery made from recycled graphite, and ZnO loaded phase change materials
This project focuses on designing and optimizing a high-performance Thermal Energy Storage (TES) system using a combination of recycled graphite, zinc oxide, and phase-change materials. The system aims to efficiently store thermal energy for applications such as industrial waste heat recovery, renewable energy and electricity integration, and building heating and cooling. It seeks to create a modular TES battery made from recycled graphite and semiconductor (ZnO) particles dispersed in phase-change materials (paraffin wax, molten salts/metal alloys) that are not only low-cost and energy-efficient but also provide a wide operating temperature range (100-800 °C), powered by renewable energy or industrial and process waste heat, depending on the area of application. The aforementioned TES battery will be constructed using recycled graphite scrap integrated with ZnO-loaded phase change materials (PCMs) to enable the utilization of sensible and latent heat transfer, enhance performance and cost-effectiveness, and demonstrate real-world applications such as industrial heat recovery and off-grid storage of solar energy/heat. The use of both graphite blocks and ZnO-loaded phase change materials as a heat storage medium allows for high (above 600 °C) and low-temperature (100-200 °C) operations, facilitating both sensible and latent heat utilization. Depending on heating requirements, the designed system will operate with and without phase change materials to offer greater operational flexibility. The proposed work can be divided into three major stages, which are described below: Stage 1 will focus on material selection for constructing the TES battery, selecting optimal phase change materials, engineering design, and development of the proposed TES battery. For material selection, multi-criteria decision-making will be employed using both subjective and objective weighting. Stage 2 will concentrate on the design and development of the setup in SolidWorks, followed by computational modeling in COMSOL for design optimization and validation. After design optimization, the prototype TES will be fabricated using suitable materials of construction (MOC). Stage 3 will involve conducting experiments to optimize operational and process parameters for effective heat storage and utilization. To justify the environmental sustainability and economic viability of the developed TES battery, a life cycle assessment and techno-economic analysis will be performed.
BITS Supervisor
Samarshi Chakraborty
RMIT Supervisor
Shiwei Zhou
Other Supervisor BITS
Dr. Sampatrao Dagu Manjare
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Civil Engineering, Structural Engineering |
| Computational Fluid Dynamics & Fluid Mechanics, Modelling |
|
Design and Development of Small Organic Molecules Based Diverse Flexible Organic Solar Cell Devices (OSCDs) Customized for Wearable Electronics
Aim/Objective:
To synthesize and develop an active layer of TCNQ derivatives (D-pi-A frameworks) for simple, flexible, biodegradable organic solar cells that could be utilized for wearable electronics.
Rationale: Utilization of aminoethyl pyridine in Aminoethylpyridine substituted TCNQ (AEPYDQ) has proven crucial in our recent study achieving the highest device efficiency of 11.75%.The enhancement in power conversion efficiency (PCE) of AEPYDQ was attributed to remarkable crystallinity with high roughness (Rq = 19.40 nm), ordered, dense molecular packing. AEPYDQ showed the presence of multiple aromatic pyridine moieties, which promotes effective stacking and extended light absorption, leading to improved current generation. The presence of an ethylene spacer helps in single-bond rotation, therefore improving the charge transport through the ICT process. Thus the selection of amine plays a crucial role, moreover, aromaticity, conjugation and flexible aliphatic moieties (help in charge transport) play an important role in achieving higher PCE. This was one of the key results as achieving ~ 11% PCE with small molecules with a single active layer was commendable when compared to OSCs achieving up to ~ 21% which includes complex molecules and polymers. Thus, the higher PCE, single-step synthesis, and cost-effectiveness of the solar cell device.
Methodology: Therefore, we aim to synthesize TCNQ derivatives with various and appropriate primary/secondary/aromatic amines. The addition of linkers has proven to increase PCE. Linkers are the aliphatic/p conjugated molecules bridging D-A molecules for accelerating electron transport. Therefore, the right choice of linkers (eg. FNE 29, DT-1, etc.) with ease of binding with our synthesized molecule is an important step. Also, polymers like PEDOT PSS, PFN-Br, etc, or TiO2 nanoparticles as charge transport layers and metal-based organic dyes (ruthenium, cobalt, zinc, etc.) as sensitizers can be utilized. The inclusion of TiO2 nanoparticles as an electron transport layer has shown a 5-fold increase in PCE in our previous work. Further, incorporating elastomers in the active layer for achieving the flexibility of OSC; polydimethylsiloxane (PDMS), styrene ethylene butylene styrene (SEBS), etc. will be considered.
Outcome: TCNQ derivatives as the active layer of DADQ (D-p-A framework) for simple, flexible, biodegradable organic solar cells employed for wearable electronics will be developed from this project.
BITS Supervisor
Jayanty Subbalakshmi, Professor
RMIT Supervisor
Sharath Sriram, Professor
Other Supervisor RMIT
Md Ataur Rahman
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Electrical and Electronics Engineering, Power Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Smart Nanofiber-Based Colorimetric Sensor with Mobile Application for CKD Detection through Urine
Chronic Kidney Disease (CKD) is a major global health issue, with 697.5 million cases reported in 2017. India alone accounts for 115.1 million cases, with a significant burden in rural areas, while 1.7 million Australians show biomedical signs of CKD. Current diagnostic methods are invasive, costly, and inaccessible in remote areas.
Objectives:
1. Design and fabricate electrospun nanofiber-based sensors functionalized with specific biomarkers for the selective detection of creatinine, albumin and cystatin C in urine samples.
2. Establish a quantitative correlation between biomarker concentration and sensor response using UV-Vis spectroscopy to enhance detection sensitivity and reliability.
3. Develop and integrate a smartphone-based mobile application with image-processing algorithms for real-time colorimetric analysis and CKD severity assessment.
4. Evaluate and compare the sensitivity and specificity of creatinine, albumin and cystatin C as biomarkers to determine the most effective indicator for CKD diagnosis.
Methodology:
1. Fabrication of Sensor
a) Electrospinning will be employed to produce high-surface-area nanofiber mats
b)The nanofibers will be chemically modified with selective reagents or dyes or nanoparticles to facilitate the specific detection of creatinine, albumin and cystatin C.
c) Optimization of fiber morphology and surface chemistry will be carried out to improve detection sensitivity and specificity.
2. Characterization and Performance Evaluation
a) UV-Vis spectroscopy will be conducted to establish a quantitative correlation between biomarker concentration and sensor response.
b) Colorimetric intensity variations will be analyzed to assess the sensitivity and accuracy of the sensor in detecting CKD biomarkers.
c) The stability and reproducibility of the sensor will be evaluated under diverse environmental conditions to ensure long-term reliability.
3. Development of a Smartphone-Based Analytical Platform
a)An image acquisition system will be developed using the smartphone’s built-in camera to capture and analyze sensor images.
b) Image processing algorithms will be integrated to quantify colorimetric changes and translate them into CKD severity levels.
c) In-the-wild testing will be performed under diverse sample conditions and varying environmental factors, such as lighting conditions, to compare sensor performance with standard laboratory techniques.
BITS Supervisor
Mrunalini Kawaduji Gaydhane, Assistant Professor
RMIT Supervisor
Sharath Sriram, Professor
Other Supervisor BITS
Manideepa Mukherjee
Other Supervisor RMIT
Ganganath Perera, Research Fellow
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Computer Vision, Image Processing, Virtual Reality |
| Data Science, Data Mining, Data Security & Data Engineering |
|
A Data-Driven Meta Model for Offshore Wind Energy Geotechnical Site Investigation
PROJECT DESCRIPTION:
Accurate geotechnical site characterization is essential for offshore wind turbine foundation design, particularly for estimating small-strain soil stiffness (G0), which governs monopile performance. Current empirical correlations between Cone Penetration Test (CPT) data and Seismic CPT (S-CPT) outputs are often inaccurate, leading to overly conservative designs, increased material costs, and suboptimal performance.
This project aims to develop an advanced data-driven meta-model by integrating machine learning (ML) with large-scale geotechnical datasets from offshore wind farms worldwide, including North Sea and Australian sites. The model will fuse physics-based principles with data-driven approaches to improve G0 estimations, optimize foundation design, and enhance site investigation methodologies.
Objectives & Methodology
1. Global Data Collection & Classification: Integrate CPT and S-CPT datasets from offshore wind farms (North Sea, US, China, Australia).
2. Developing Improved CPT-to-Stiffness Correlations: Evaluate existing empirical CPT-Vs correlations and introduce ML-based stress-dependent models for offshore-specific conditions.
3. Machine Learning-Based Meta-Model: Implement multi-fidelity data fusion combining physics-informed ML algorithms for enhanced prediction accuracy.
4. Investigating Calcareous Sand Behavior: Collect data and conduct element testing (direct shear and triaxial tests) to improve understanding of challenging calcareous soils, which pose unique geotechnical challenges for offshore wind foundations.
5. Field & Experimental Data for Meta-Model Development: Incorporate full-scale offshore site investigations, laboratory test results, and in-situ monitoring data to validate and refine the predictive meta-model.
Global & Australian Impact
1. Advancing Global Offshore Wind: With offshore wind capacity set to triple by 2028, cost-efficient, data-driven foundation designs are essential.
2. Optimizing Design & Sustainability: Improved stiffness predictions will reduce overdesign, cut carbon emissions, and optimize material use, lowering costs.
3. Tackling Complex Soil Conditions: Calcareous sands, prevalent in Australia and beyond, require specialized models for accurate geotechnical assessment.
Supporting Australia’s Offshore Wind
4. Growth: High-fidelity ML-based predictions will address geotechnical uncertainties, reducing foundation costs and enabling planned expansions (2 GW by 2032, 9 GW by 2040).
BITS Supervisor
Dr. Sayantan Chakraborty
RMIT Supervisor
Mohammad Aminpour
Other Supervisor RMIT
Dr. Dilan Robert
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Civil Engineering, Structural Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
|
Development of Advanced Vibration Sensors based on High-Performance Graphdiyne/Polymer Nanocomposites
Recent years have witnessed rapid development of new two-dimensional (2D) carbon materials, such as graphyne and graphdiyne. Graphdiyne is an allotrope of graphene, consisting of diacetylene linkages and carbon-carbon sp2 bonds. Owing to its unique nanostructure, it has ultralow density and outstanding sensing performance. One of its promising applications (incorporating into polymer matrix for nanocomposites) is in structural health monitoring (SHM) system as vibration sensors.
In order to ensure the safety, reliability and longevity of infrastructures (e.g. bridges, buildings, dams, and aerospace systems), it is critical to have highly sensitive sensors installed in SHM, so that early detection of small damages and prevention of catastrophic failure become possible. The performance of sensors is largely determined by wave propagation properties of the materials (frequency, velocity, attenuation, phase, etc.) and their response to the environment, such as temperature, stress and pressure. The project will focus on graphdiyne and graphidyne/polymer nanocomposites design, property prediction, performance evaluation and metamaterial design of sensors by developing new multiscale modelling framework. To accelerate the design process, Physics-Informed Neural Network (PINN) will be developed based on the theoretical modelling results using strain-gradient and nonlocal theories. These two theories incorporate higher-order-stress-strain relationship and small-scale effects, allowing for more accurate characterization of the wave propagation in the graphdiyne/polymer nanocomposites. Meanwhile, on the basis of Molecular Dynamics (MD) simulations and Finite Element Method (FEM), Genetic Programming (GP) will be developed to facilitate the inverse design of the sensors with the best sensing performance. This is a proof-of-concept research consisting of multidisciplinary disciplines, including solid mechanics, nanoscale simulation, finite element modelling, and machine learning. The research outcomes will contribute to the development of highly sensitive SHM systems critical to various industries where safety is of paramount importance.
BITS Supervisor
Prof. Sumit Kumar Vishwakarma
RMIT Supervisor
Yingyan Zhang
Other Supervisor BITS
Brajesh Panigrahi
Required discipline background of candidate
| Discipline |
| Materials Science |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mathematical Sciences |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Smart Marine Vessels for AI-Driven Plastic Clean-up
Summary
Plastic pollution is a planetary problem. The Smart Surface Ships for AI-Powered Plastic Cleanup project aims to develop and deploy autonomous surface vessels equipped with artificial intelligence (AI) for efficient plastic waste detection and collection in water bodies. This initiative addresses the growing environmental crisis of plastic pollution in oceans, rivers, and lakes by leveraging advanced robotics, machine learning, and sensor technologies.
The primary objectives of this project are:
1. Autonomous Navigation & Operation: Develop AI-driven surface vessels capable of autonomously navigating through water bodies while avoiding obstacles and adapting to environmental conditions.
2. Plastic Waste Detection: Implement computer vision and deep learning algorithms to detect, classify, and differentiate plastic debris from other floating objects.
3. Efficient Collection Mechanism: Design and integrate a smart retrieval system that captures floating plastics without harming aquatic life.
4. Data Collection & Monitoring: Utilize onboard sensors to collect real-time data on plastic waste distribution, contributing to environmental research and clean-up planning.
5. Scalability & Deployment: Ensure modular and cost-effective designs for large-scale implementation across various water bodies.
Methodology
The project will follow a structured approach:
• AI & Machine Learning Integration: Train deep learning models using datasets of floating plastics to improve detection accuracy.
• Autonomous Vessel Development: Design and fabricate an energy-efficient, solar-powered surface vehicle with adaptive control algorithms.
• Sensor & Computer Vision Systems: Employ LiDAR, cameras, and hyperspectral imaging for real-time waste identification.
• Mechanical Collection System: Engineer an optimized robotic arm/manipulator for efficient plastic retrieval.
• Field Testing & Optimization: Conduct trials in controlled and real-world environments to refine AI models and operational efficiency.
This innovative approach will significantly enhance plastic cleanup efforts, reducing marine pollution and contributing to global sustainability goals.
BITS Supervisor
Prasad Vinayak Patil
RMIT Supervisor
Tanveer Adyel
Required discipline background of candidate
| Discipline |
| Computer Vision, Image Processing, Virtual Reality |
| Electrical and Electronics Engineering, Power Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
Digital twin incorporating AI Features for the prediction of sub-surface damage and fatigue life of the machined components
BACKGROUND
Surface integrity and tool wear characteristics are very important quality indicators of machining when viewed from many perspectives. The surface integrity characteristics of a machined surface basically constitute surface roughness, surface defects, microstructure alterations, particularly in the Heat Affected Zones (HAZs) in the proximity of the machined surface and mechanical properties (strain hardening formation and microhardness, residual stress). These features have a significant effect on the functional properties (fatigue life, toughness creep, corrosion) of the part when it is subjected to a process or during its life as a final product.
AIM
In this project, a credible Digital Twin (DT) of the Machining process to account for the aforementioned surface integrity characteristics and its effects on mechanical performance (such as fatigue life, toughness creep, corrosion) will be developed. This Digital Twin (AI) will incorporate Artificial Intelligence (AI) features to predict the sub-surface damage and fatigue life of machined components.
METHODOLOGY
The Digital Twin (DT) includes a set of adaptive models capable of simulating the behaviour of a physical system by developing a virtual system while receiving real-time data (from physical laboratory experiments) to update itself throughout its life cycle. The DT will simulate the physical system to predict failures and opportunities for change and prescribe real-time actions for optimising and/or mitigating unexpected events while also observing and evaluating the operating profile system. DT can approximate the physical system's behaviour (static feature) during simulation and duplicate and imitate the physical system's actual behaviour (dynamic feature) during emulation. The AI features planned in this Digital Twin model will introduce predictable abilities, which hitherto were not possible from deterministic physics-based models, such as the surface finish relationship to fatigue resistance. The proposed work aims at developing a digital twin with AI features of the machining process and reliably predict tool wear and machine-induced surface damages that could lead to a poor mechanical performance in service.
BITS Supervisor
SABAREESH GEETHA RAJASEKHARAN , Associate Professor
RMIT Supervisor
Sabu John, Professor
Other Supervisor BITS
Amrita Priyadarshini, Associate Professor
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
|
Structure-Function Relationship of a Flippase-conjugated Guanylate Cyclase in Toxoplasma gondii
The architecture and functioning of cGMP signaling is well characterized in metazoans, but poorly understood in protozoans. Some intracellular parasitic protists harbor chimeric proteins embodying P4-type ATPase and guanylate cyclase domains. Such proteins – the actuator of physiologically-essential and druggable cGMP signaling in this group of clinically relevant important pathogens – are unusual in their sheer size, modus operandi, and evolutionary repurposing. Much like the mythological Sphinx, a human-lion chimeric creature that posed challenging riddles, the P4-type ATPase–guanylate cyclase chimeras present structural and functional conundrums. In this project, we combine the expertise of two PIs and two co-PIs at BITS-RMIT to address the function, topology, mechanism, and intramolecular coordination of the flippase-conjugated guanylate cyclase from the model protozoan pathogen Toxoplasma gondii. We will express and purify the functional domains in bacterial and mammalian systems and then crystallize them to resolve the mechanism and functionality of this protein. In parallel, we will also aim to perform structure determination of the native protein in complex with interaction partners isolated from T. gondii.
BITS Supervisor
Nishith Gupta, Professor
RMIT Supervisor
Natalie Borg
Other Supervisor BITS
Ratnesh Kumar Srivastav, Dr.
Other Supervisor RMIT
Dr Charlett Giuliani
Required discipline background of candidate
| Discipline |
| Biological Sciences |
| Biology, Cell Biology, Niological Sciences |
| Biomedical Sciences |
|
Application of Machine Learning for Generation of Characteristic Elastic Waves in Porous and Functionally Graded Composite Structures
Elastic wave propagation plays a crucial role in various engineering applications, including structural health monitoring (SHM), non-destructive evaluation (NDE), biomedical imaging, and geophysics. Functionally graded materials (FGMs) and porous composites exhibit unique mechanical properties that influence wave dispersion, attenuation, and interactions with defects. Understanding and accurately modeling these wave characteristics are essential for optimizing material design in aerospace, civil engineering, and energy harvesting. Traditional analytical and numerical models often fail to capture the complex spatial variations in these materials, necessitating advanced computational and data-driven approaches.
With recent advancements in machine learning (ML), there is significant potential to enhance wave generation and propagation modeling in graded and porous structures. ML-based techniques can identify hidden patterns in wave behavior, optimize computational efficiency, and improve predictive accuracy beyond conventional numerical methods. This project aims to integrate ML algorithms with computational techniques such as the Finite Element Method (FEM), Spectral Element Method (SEM), and Meshless Methods to develop a robust framework for wave modeling and generation.
Key Research Objectives:
Develop ML-assisted mathematical and numerical models incorporating spatial variations and complex boundary conditions.
Utilize ML-driven approaches to optimize wave dispersion and attenuation for vibration damping and impact resistance.
Leverage deep learning techniques to analyze wave-defect interactions, enhancing NDE and SHM methodologies.
Implement multiscale ML models linking microscale porosity to macroscale wave propagation behavior.
Integrate environmental factors such as initial stress, thermal gradients, and fluid saturation into ML-driven predictive models for greater accuracy.
By combining physics-based modeling with ML techniques, this research aims to address existing gaps in computational wave mechanics, improve predictive capabilities, and enhance the practical applicability of elastic wave-based technologies in real-world scenarios.
BITS Supervisor
Prof. Sumit Kumar Vishwakarma
RMIT Supervisor
Dr. Tu Le
Other Supervisor BITS
Brajesh Panigrahi
Other Supervisor RMIT
Akbar Khatibi
Required discipline background of candidate
| Discipline |
| Materials Science |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mathematical Sciences |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Creation of S- Scheme heterojunctions with tuned bandgap energy by combining two 2-D semiconductor nanoparticles: Efficient photo-electrocatalysts for e-Methanol production from CO2 at low bias and solar light
Main Objective:
Design and synthesis of S- Scheme heterojunctions with tuned bandgap energy by combining two semiconductor nanoparticles, which can exhibit high photoelectrocatalytic efficiency for e-Methanol production from CO2 at low bias and solar light exposure.
(1) Design of nanostructured S-scheme heterojunctions by combining two 2-D semiconductor nanoparticles.
(2) Bandgap engineering of these S-scheme heterojunctions by judiciously choosing semiconductors with suitable band positions (conduction band and valence band).
(3) Evaluation of the photoelectrocatalytic performances of the synthesized heterojunctions for e-Methanol production from CO2 at low bias and solar light exposure.
Methodology
Task -1 Development of synthesis methodologies to create suitable heterojunctions by forming hierarchical heterostructures by combining two 2-D semiconductors ((i.e., Potassium poly(heptazineimide) (K-PHI), gC3N4, hexagonal boron nitride, MoS2, etc).
Task 2: Tuning the band gap, and band positions (CB and VB) by controlling the nature, compositions, and microstructures of the semiconducting nanomaterials.
Task 3: Structural characterizations of the synthesized materials by using XRD, XPS, FESEM, HRTEM, Raman Spectroscopy, FTIR, UV-Vis DRS, etc.
Task 4: Investigations on the photoelectrocatalytic efficiency of the synthesized materials for e-Methanol production from CO2 at low bias and solar light exposure by determining overpotential, onset potential, Tafel slope, Turnover Frequency, Mass activity, electrochemically active surface area, roughness factor, specific activity, stability of the electrocatalyst, etc.
Task 5: Determination of the rate of the reaction by analyzing the production of methanol with time by using solution NMR techniques.
Task 6: DFT calculations to understand the electronic structures of the heterojunctions and their influence on the performance of the catalyst.
BITS Supervisor
Dr NARENDRA NATH GHOSH and Professor
RMIT Supervisor
Dr Derek Hao and Vice Chancellor’s Postdoctoral Fellowship
Required discipline background of candidate
| Discipline |
| Chemistry or Chemical Sciences |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Enhancing Market Growth and Supply Chain Resilience in the Electric Vehicle Ecosystem of India
The automobile sector plays a crucial role in India's economic development by generating employment opportunities. According to the Society of Indian Automobile Manufacturers (SIAM), the Indian automobile sector, one of the fastest-growing industries in the country, contributes approximately 6% to the Gross Domestic Product (GDP). More significantly, it accounts for nearly 50% of India's manufacturing output and provides employment to over 35 million individuals. However, this growth has also been accompanied by a substantial rise in CO2 emissions, closely linked to the increasing number of registered motor vehicles.
To address these environmental concerns, the adoption of electric vehicles (EVs), widely recognized as zero-emission vehicles, has emerged as a viable alternative to conventional internal combustion engine (ICE) vehicles. In response, the Government of India has set ambitious targets, aiming for 40% of all private vehicles and 100% of public transport to be electric by 2030. Furthermore, the Indian automotive sector has outlined a strategic vision to transition entirely to EV production by 2047, coinciding with the nation’s centennial independence anniversary.
As India's EV ecosystem continues to evolve, the integration of Artificial Intelligence (AI) and Machine Learning (ML) is poised to play a transformative role in understanding and forecasting for accelerating adoption, ensuring economic stability, and fostering a sustainable ecosystem in the transport sector. In this study, four key dimensions such as demand forecasting, pricing optimization, supply chain resilience, and policy implementation will be studied using AI/ML techniques in the EV landscape for its enhancement
BITS Supervisor
Krishna Muniyoor, Associate Professor
RMIT Supervisor
Muhammad Abdulrahman
Other Supervisor BITS
Professor Srikanta Routroy
Other Supervisor RMIT
Dr. Kamrul Ahsan
Required discipline background of candidate
| Discipline |
| Economics |
| MBA (Operations / Supply Chain and Logistics) |
| ME (Industrial/Production Engineering) |
| Sustainable Development, Development Studies, Development Geography, International Development |
|
Machine Learning-integrated DFT investigation of engineered 2D-material for supercapacitor electrode design
The ever-increasing requirements for energy storage units for industries have driven the research and development in supercapacitors in the last couple of decades. However, one of the major challenges in supercapacitor technology lies in its relatively low energy density, which is directly proportional to the specific capacitance. In recent times, specific capacitance improvement through the optimization of electrode materials is at the forefront of supercapacitor research. In this effect, the proposed project focuses on comprehensive theoretical investigations of MXenes, an emerging member of the 2D material family, for high performance EDL supercapacitor electrode design focusing on the experimental synthesis aspects of MXenes. In this context, the proposed research represents the original and transformative approach by addressing the following objectives:
1. Investigate the effects of different experimentally observed defects on the electronic properties and subsequently on the electrode performance of MXenes.
2. Systematically analyze the feasibility of introducing different doping species, dynamic/ thermal/ structural stabilities under different doping/co-doping, and doping-defect interactions on the electronic properties and electrode performance of the engineered MXenes.
3. Develop a robust DFT data-set driven ML-based predictive framework for simultaneously assessing the doping formation energy, specific surface area, excess charge density, quantum capacitance, charge storage capacity over a range of defect/doping configurations and concentrations.
4. Develop an extensive material library for screening and optimizing promising engineered MXenes for experimental realization of high performance EDL supercapacitor electrodes.
The topic will be studied through integrated approach involving DFT simulation using the VASP, and ML based predictive modelling using MATLAB tool suite/ Python platform. Different phases of this proposed research will be arranged in work packages as follows:
WP-1: Ab-initio modelling and electrode performance assessment of defective MXenes
WP-2: Ab-initio modelling and electrode performance assessment of doped MXenes in presence of defects
WP-3: Machine learning based predictive modelling of doping feasibility and electrode performance over different doping/defect concentrations in MXenes
WP-4: Material library development for screening and optimization of MXenes for experimental synthesis
BITS Supervisor
Dr. Ankur Bhattacharjee
RMIT Supervisor
Dr. Tu Le
Other Supervisor BITS
Dr. Sayan Kanungo
Other Supervisor RMIT
Dr. Ravichandar Babarao
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
EV-PCR: Enhancing Urban Mobility by Integrating Electric Vehicles in Park, Charge, and Ride System
The transportation sector accounts for 24% of global CO2 emissions, with road transport contributing 45.1% due to fossil fuel vehicles (ICEVs). Rising private vehicle ownership and the COVID-19 pandemic have exacerbated transport emissions and urban congestion. In response, electric vehicles (EVs) have emerged as a sustainable alternative, with many countries aiming for 100% EV adoption by 2050. India targets 30% EV adoption through initiatives like the Faster Adoption and Manufacturing of Hybrid and Electric Vehicles (FAME) and the Pradhan Mantri Electric Vehicle Driving Awareness and Incentive Scheme (PM E-DRIVE). Similarly, Australia aspires for 100% EVs in new registrations under the National Electric Vehicle Strategy (NEVS). Nonetheless, challenges like high purchase costs, range anxiety, and inadequate charging infrastructure continue to hinder this transition.
Integrating electric vehicles (EVs) with public transport in a park-charge-ride (PCR) package can enhance EV adoption and ridership. This package allows private EV users to drive to charging stations at transit stops, park their vehicles, and take public transport to their destination. Despite its potential, the feasibility and public perceptions of EV-PCR integration remain unexplored. The proposed research aims to assess EV-PCR feasibility in India and Australia through exchange visits, commuter & stakeholder surveys, field visits, and stakeholder engagement. Key objectives include evaluating current park & ride and PCR infrastructure, identifying gaps, understanding commuters' and transit agencies’ preferences, and developing strategies to enhance user satisfaction and boost EV-PCR adoption. The research will focus on Hyderabad, which experiences high levels of traffic congestion despite its expanding public transport, and Melbourne, which also grapples with rising congestion despite a strong integrated transport network. The methodology involves assessing infrastructure and commuter preferences through a virtual reality-based questionnaire and advanced modeling techniques like multicriteria decision-making, econometric, and AI/ML-based approaches, with commuter preferences primarily explored in Hyderabad as part of existing funding available with the Indian PI. Implementing EV-PCR at major transit stations can significantly promote sustainable mobility, reducing urban transport emissions by 75-80% and enhancing transit accessibility.
BITS Supervisor
Dr. Ishant Sharma, Assistant Professor
RMIT Supervisor
Dr. Chris De Gruyter, Senior Research Fellow
Other Supervisor BITS
Dr. Prasanta Kumar Sahu, Associate Professor
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
| Economics |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
| Urban Development, Regional Planning |
|
Laser Micromachining of Superhydrophobic Surfaces to Combat Bacterial Infections
Bacterial infections pose a significant challenge in biomedical applications, particularly in medical implants and high-contact surfaces. Conventional antibacterial coatings often lose effectiveness over time and may contribute to antibiotic resistance. Superhydrophobic surfaces, inspired by nature (e.g., lotus leaves, cicada wings), have shown great potential in preventing bacterial adhesion through physical mechanisms rather than chemical agents. This proposal focuses on the development of superhydrophobic surfaces using laser micromachining, combined with finite element analysis (FEA) and computational fluid dynamics (CFD) simulations, to optimize surface design and fluid interaction for enhanced antibacterial properties.
BITS Supervisor
Dr. Nithin Tom Mathew
RMIT Supervisor
Xiaobo Chen
Other Supervisor BITS
Priyank Upadhyaya
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Computational Fluid Dynamics & Fluid Mechanics, Modelling |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Development of an Intelligent Pipe-Climbing Robot for Pipeline Inspection
Water pipeline inspection in India faces several unique challenges due to a combination of infrastructure, environmental, and socio-economic factors. Many water supply networks in India are decades old, leading to corrosion, scaling, and frequent leaks. Lack of detailed mapping of underground pipelines, dense urban areas complicate inspection and maintenance. Road congestion and infrastructure development increase the risk of pipeline damage during construction activities.
Variation in pipe diameters adds complexity to deploying robotic systems or sensors. Dependency on manual inspection methods that are time-consuming and less accurate. Limited use of modern inspection technologies like robotic crawlers, smart sensors, or advanced leak detection systems due to budget constraints.
A robotic system with sensors can navigate through pipelines and detect issues like cracks, corrosion, blockages, and leaks. This robot is highly effective for inspecting hard-to-reach areas, minimizing human risk, and providing accurate data. There are several sensors used for pipe inspection, a remote-controlled camera can identify cracks, blockages, and corrosion; Ultrasonic Testing can detect wall thickness, corrosion, and other internal defects; magnetic fields can detect metal loss or corrosion and leak detection systems using sensors or acoustic equipment.
Several robotic systems equipped with advanced sensors are available for inspecting water supply pipelines. All the commercially available robots are having limitations of mobility in vertical climbing, sharp bends and T-junctions, etc. We want to develop a pipe climbing robot prototype, which can overcome the above mentioned limitations and increase the flexibility of accessing critical locations of a pipe network.
Objectives:
Study the scope of different types of pipe climbing robot for pipeline inspection,
Design and development of the prototype of the pipe inspection robot,
Incorporation of sensors and collection of data for scaling, internal crack, and pipe defects,
Analysis of the sensor data for monitoring and evaluation of the pipe condition.
Methodology:
A pipe climbing robot prototype will be designed and developed as per the desired pipe diameter.
Sensors and a camera will be attached on the pipe climbing robot.
The robot will be deployed inside the pipe network for collecting the sensor data.
The sensor data and visual data will be used to train a machine learning model for the detection of defects.
BITS Supervisor
Abhishek Sarkar
RMIT Supervisor
Professor Alireza Bab-Hadiashar
Other Supervisor BITS
Vasan Arunachalam
Required discipline background of candidate
| Discipline |
| Artificial Intelligence |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
An Autonomous Robotic Ultrasound Imaging System
In robotic ultrasound, the ultrasonic probes are attached to the robot end-effector. The fusion of robotics and ultrasound systems allows for enhanced precision and consistency, improved accessibility, remote operation and telemedicine, reduced operator fatigue and minimally invasive procedures. Robotic ultrasound can be combined with artificial intelligence (AI) algorithms to provide real-time guidance, automatic identification of anatomical landmarks, and enhanced diagnostic accuracy. This can lead to more effective and early detection of diseases. In the proposed PhD project, for the development of ultrasound probes, the use of microelectromechanical systems (MEMS) technology will be explored in place of traditional bulk transducers. The advantages of MEMS devices include low-size, low-weight and low power consumption. MEMS-based ultrasound transducers (MUT) can be produced via a low-cost, flexible and reproducible manufacturing process allowing for rich experimental explorations. These miniaturised transducers also overcome many performance limitations of bulk transducers including high-frequency of operation and acoustic impedance matching to biological tissues. The MUT devices can be either piezoelectrically or capacitively driven. The benefit of piezoelectrically driven MUT (PMUT) devices is the lack of high-bias voltage. Due to their small size and ability to form dense arrays, PMUTs are capable of advanced beamforming and steering, which can improve the precision of imaging.
The objectives of the project are as follows. The first two objectives will be achieved at BITS and the last objective will be achieved at RMIT.
1. Design and Development of PMUT Devices for Medical Imaging
- The PMUT devices will be first simulated in COMSOL Multiphysics and MATLAB/Mathematica respectively. The final PMUT designs will be fabricated in MEMSCAP foundry.
2: Experimental Validation of PMUT Devices for Medical Imaging
- The fabricated PMUT devices will be characterised in the electronics laboratory. Thereafter, the capability of PMUT devices for medical imaging applications will be assessed.
3: Application of Robotic Manipulators and Computer Vision for Medical Imaging and Diagnostics
- The PMUT devices will be integrated to the end-effector of robots for enabling autonomous imaging system. Following that, computer vision tasks including medical image classification, shape and object recognition from images, and medical segmentation will be achieved.
BITS Supervisor
Prof. Adarsh Ganesan
RMIT Supervisor
Prof. Ruwan Tennakoon
Other Supervisor BITS
Dr.V.Kalaichelvi, Professor
Required discipline background of candidate
| Discipline |
| Computer Science and Engineering/Computer Engineering |
| Computer Vision, Image Processing, Virtual Reality |
| Engineering, Engineering Physics |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
AI-Based Federated Power Plants for Electric Vehicles: Enhancing Energy Management and Grid Stability
Summary
AI-Based Federated Power Plants (FPPs) represent a cutting-edge approach that could significantly improve energy management, EV integration, and grid stability. These decentralized systems can leverage artificial intelligence (AI) to optimize energy generation, distribution, and consumption, with a special focus on managing EV charging and discharging. Federated Learning (FL), a machine learning technique that allows for model training across distributed systems without sharing raw data, enables privacy-preserving collaboration between power plants, EVs, and charging stations. This project aims to explore the following research contents:
Aims:
1) Development of distributed energy resources (DERs) integrated within a federated framework
2) Development of AI models for EV charging optimization and V2G integration
3) Implementation of Federated Learning model on the integrate model with EVs and renewable resources and training for energy optimization
4) Grid simulation and resilience analysis to evaluate grid stability, energy efficiency, and privacy
Methodology:
1) System Design and Framework Development in MATLAB: The Federated Power Plants system architecture would be defined with various energy sources (e.g., solar, wind, battery storage, microgrids).
2) In the developed model, EV charging points would be identified for their interaction with the grid (i.e., Vehicle-to-Grid (V2G) functionality, with bidirectional charging, and demand-side management).
3) A grid interface will be developed to monitor and control power flow between FPPs, EVs, and the utility grid.
4) An AI-based algorithms (for time series date) will be developed that will predict and optimize the charging and discharging schedules of EVs which will also include models to allow bidirectional power flow between EVs and the grid to engage V2G, based on grid conditions and EV battery state-of-charge.
5) Federated Learning Framework will be implementation to allow power plants, EV charging stations, and renewable energy resources to train AI models on their local datasets without sharing raw data.
6) Use real-world data simulations (with support of PSCAD, DIGSILENT, MATLAB) for evaluating how well the AI-based FPP system performs in a variety of grid scenarios (e.g., high demand, renewable energy variability, EV integration).
7) Simulate emergency scenarios (e.g., grid outages) to test the resilience of the system.
BITS Supervisor
Dr. Alivelu Manga Parimi
RMIT Supervisor
Dr Manoj Datta, Senior Lecturer
Other Supervisor RMIT
Dr. Kazi Hasan
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
|
Prevalence and Impact of Sleep Disorders in the Indian Population
Introduction:
Sleep disorders remain a rising health issue in India, with studies showing that conditions like Obstructive Sleep Apnea (OSA) impact 104 million adult population with an increased prevalence amongst men. Studies point to associations between sleep problems, metabolic disorders, diabetes risk, and cognitive performance. Poor sleep takes a toll on mood and academics as well, especially among adolescents. Awareness is low at the level of the general public, where only 27% of Indians claim to have a sound sleep, and misbeliefs like snoring being a sign of good sleep are prevalent. Greater awareness, earlier diagnosis, and improved sleep health management are sorely needed.
Relevance of Study:
Sleep is vital for the overall health of an individual, but sleep disorders in India are poorly diagnosed and treated. Previous studies estimated the prevalence of OSA among Indian adults to be around 11 percent, with a substantial proportion being affected by insomnia and RLS. This study will add to the evidence base on the burden of sleep disorders and the broader implications for health and well-being.
Experimental Setup:
Sleep labs or Sleep centers are currently used to diagnose and monitor sleep disorders. However, these are expensive and only available in large medical centers. We propose an alternative method, where patients' sleep can be monitored in their homes using a minimally intrusive electrocardiogram and photoplethysmograph (PPG). We will use these inexpensive devices to record the data to assess for Obstructive Sleep Apnea (OSA), insomnia, restless legs syndrome (RLS), narcolepsy, and circadian rhythm disorders.
Equipment:
1. Photoplethysmograph (PPG): Measures brain activity, oxygen levels, heart rate, and muscle activity while asleep.
2. Multiple Sleep Latency Test (MSLT): To measure daytime sleepiness, generally used to diagnose narcolepsy.
3. HSAT (Home Sleep Apnea Testing): Portable sleep apnea test done outside the lab.
4. Video Monitoring. Records body movements and behaviors during sleep.
Objectives:
1. To find out the various demographic details for sleep disorders in the Indian population.
2. To determine the association of sleep disorders with metabolic health, cognitive function, and psychological well-being.
3. To assess public awareness and attitudes towards sleep health.
4. To suggest strategies to increase awareness of and treatment for sleep health.
5. To correlate OSA with maternal health
BITS Supervisor
T S L Radhika
RMIT Supervisor
Prof Dinesh Kumar
Other Supervisor BITS
DR K Naga Jyothi
Other Supervisor RMIT
Professor Feng Xia
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Biomedical Science and Biotechnology |
| Data Science, Data Mining, Data Security & Data Engineering |
| Health, Digital Health |
|
EVALUATING THE EFFECT OF QUINACRINE ON ANGIOGENESIS AND METASTASIS IN NON-SMALL CELL LUNG CANCER CELLS
Lung cancer is one of the leading causes of cancer-related mortalities worldwide. Despite all the breakthrough technologies and drug inventions, the 5-year survival rate is quite poor. Traditionally, alkylating and DNA binding drugs such as cisplatin and doxorubicin were used for treatment along with radiation therapy, but current treatment trends include inhibitors of key proteins which play an important role in oncogenic processes such as Avastin (VEGFR2 peptide inhibitor), erlotinib (EGFR inhibitor), as well as immunotherapy. Data available shows worrying figures of resistance acquired in patients across spectrum of drugs. Modulators of actin cytoskeleton namely RhoGTPases, Matrix metalloproteinases (MMPs), angiogenic factors and markers especially vascular endothelial growth factor (VEGF and VEGFRs) play a pivotal role in the metastatic spread of cancer.
A new concept widely tested and explored among clinicians and researchers is the use of combinational therapy for cancer treatment. Quinacrine (QC), a 9-aminoacridine compound is one of the popular anti-malarial drugs which has been repurposed and explored for its anti-cancer potential. In vitro studies performed on various cancer lineages have shown that QC acts mainly via suppressing NF-kB and activating p53 signalling in cancer cells. A hallmark of cancer is the ability of these malignant cells to evade apoptosis. Cancer cells exhibit many characteristics that would readily trigger apoptosis in healthy cells-for example, they violate cell cycle checkpoints and can withstand exposure to cytotoxic agents. Avoiding apoptosis is integral to tumor development and resistance to therapy. Cancer cells possess a unique ability to adapt to different environmental conditions, assuming different morphologies and migration characteristics to stay motile. In-vivo, motile tumor cells have been observed to migrate individually as single cells, as loosely attached cell streams and as well-organized, adherent collectives.
We will focus initially on the effect of QC on cell viability, mode of cell death, effect on tumor cell cycle check points as well as cell motility. We will examine the mechanism(s) by which it exerts these effects using human non-small cell lung cancer cell lines namely A549 and NCI H520, as well as non-cancerous human lung epithelial cells.
BITS Supervisor
Professor Angshuman Sarkar
RMIT Supervisor
Professor Terrence Piva
Other Supervisor BITS
Sukanta Mondal
Required discipline background of candidate
| Discipline |
| Biochemistry, Bioengineering, Biomaterials, Biotech, Biomed Eng/Sciences, Bioinformatics |
| Bioinformatics |
| Biological Sciences |
| Biology, Cell Biology, Niological Sciences |
| Biomedical Sciences |
| Biotechnology |
|
Machine Learning-Integrated Semi-Active Vehicle Suspension Control
This research focuses on developing machine learning-integrated controllers for semi-active suspension systems using magneto-rheological (MR) dampers in a half-car model. The primary aim is to enhance ride comfort, vehicle stability, and tire-road contact by designing adaptive control strategies that optimize suspension performance under varying road conditions.
Aims:
Develop a mathematical model incorporating tire-road separation dynamics to improve suspension performance analysis.
Design and compare multiple control strategies (PID, H-8, sliding mode, feedback linearization, and preview controllers) for semi-active suspension tuning.
Optimize PID control parameters using Particle Swarm Optimization (PSO) to minimize tire-road separation time and enhance ride quality.
Integrate machine learning (ML) models to predict tire-road separation events and dynamically adjust suspension settings.
Validate the effectiveness of ML-driven control strategies through Simulink-based simulations and experimental testing.
Methodology:
Phase 1: Literature review and identification of gaps in semi-active suspension control and ML-based predictive modeling.
Phase 2: Develop a nonlinear half-car mathematical model incorporating stochastic road inputs and high-frequency excitations.
Phase 3: Design control strategies, optimize PID controllers using PSO, and implement ML-based adaptive tuning models.
Phase 4: Simulate the system using MATLAB/Simulink, conduct transient response and frequency analysis, and validate results with experimental data.
Phase 5: Compare ML-based suspension tuning with conventional control methods and recommend improvements for real-world deployment.
This project aims to bridge the gap between traditional suspension control and AI-driven predictive optimization, offering a robust and adaptable solution for next-generation vehicle dynamics.
BITS Supervisor
PRAVIN M SINGRU
RMIT Supervisor
Dr. Hormoz Marzbani
Other Supervisor RMIT
Reza Nakhaie Jazar
Required discipline background of candidate
| Discipline |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
{Environmental Effects on Species Distribution: Integrating Species Distribution Models (SDMs) and Adaptive Dynamics
Understanding the distribution of species in response to environmental changes is a critical and essential area of ecological research. Climate change is one of the most pressing global challenges, with profound effects on ecosystems, biodiversity, and species distribution. Investigation on how climate change affects species distribution is crucial for biodiversity conservation, ecosystem management, and future-proofing conservation strategies.
Species Distribution Models (SDMs) have been widely used to predict species presence based on environmental variables, but they typically assume a static correlation between species occurrence and environmental variables and often do not incorporate evolutionary adaptations. In contrast, Adaptive Dynamics Models (ADMs) capture how species evolve and adapt to environmental stressors over time but do not predict species distribution. This study proposes an integrative and innovative approach that combines SDMs with adaptive dynamics to model species’ evolutionary responses to environmental variability, competition, and migration. This research aims to improve certainty in species distribution forecasts by incorporating adaptive potential into suitability predictions. This approach enhances the modeling of complex interactions between environmental factors, species traits, and climate change scenarios. By combining these methods, we can more accurately predict future biodiversity hotspots, identify at-risk areas, and model species' evolutionary responses to climate pressures.
We will develop a comprehensive mathematical modeling framework for integrating species distribution models (SDMs) with adaptive dynamics models (ADMs). Our approach begins with constructing a baseline SDM using machine learning or statistical models to predict habitat suitability based on key environmental predictors. Next, we will extract ADM outputs to enhance the SDM by identifying key evolutionary traits such as selection pressure, mutation rates, genetic variation, and heritability. A central focus of this project is to develop a robust, dynamic SDM that explicitly accounts for adaptive evolution. The integrated ADM with SDM model will be applied to species, such as marine organisms, migratory birds, and niche-specific fish species, as these species are particularly vulnerable to climate fluctuations, habitat loss, and shifting ecological interactions, making them ideal candidates for study.
BITS Supervisor
Anushaya Mohapatra
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Mathematical Science |
| Mathematical Sciences |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
| Neural Networks |
|
Exploring the Potential of Quantum Machine Learning Algorithms
Quantum machine learning leverages the unique properties of quantum mechanics to achieve more efficient solutions to complex problems than classical machine learning can provide. The parallelization and ability to hold large amounts of data in many states simultaneously has enormous potential to enhance optimization, pattern detection, and data analysis. It is hoped that employing quantum principles will enable machine learning models to address tasks that currently lie beyond the range of classical computers due to their exponential complexity or computational resource requirements.
Our research focuses on numerically modeling biological systems, particularly the blood flow within the carotid and femoral arteries. These models were designed to account for the arteries' complex geometry, varying vascular dimensions, bifurcations, material properties, and the diverse characteristics of blood. We utilized these developed models to simulate blood flow across different conditions within human arteries, both idealized and patient-specific, with model inputs drawn from the available clinical data.
some of our studies necessitated working with the entire feature set, comprising highly correlated features for which we adopted regularized regression models or ensemble methods. Nonetheless, the difficulty persisted in generating robust datasets for adequately training classical ML algorithms due to the substantial computational resources and time demanded by the simulations. In our first attempt, we applied a linear regression model to one of the datasets for which the quantum version gave poor metrics, denying its ability to be a good predictor model. In contrast, classical ML gave us good metrics. However, when we tested the underlying assumptions, residual plots showed patterns indicating that it is not a reliable predictive model for our purpose [17]. This indicated the efficiency of Quantum inspired ML algorithms that led us to consider leveraging the capabilities of Quantum Machine Learning (QML) algorithms to the medical datasets available to our group and raise the following questions:
1. Considering the remarkable feature of quantum computing—ENTANGLEMENT—, do basic regressor models adequately predict target variables when the feature set is uncorrelated?
2. Can QML offer more efficient solutions for managing correlated feature sets than classical approaches?
3.Is it possible for "Quantum Parallelism" to enhance predictions when dealing with limited data
BITS Supervisor
T S L Radhika
RMIT Supervisor
Prof Dinesh Kumar
Other Supervisor RMIT
Akram Hourani, Professor
Required discipline background of candidate
| Discipline |
| Computer Science and Engineering/Computer Engineering |
| Computer Science/Information Technology |
| Data Science, Data Mining, Data Security & Data Engineering |
| Engineering, Engineering Physics |
|
Theoretical modeling of electronic and transport properties of engineered 2D topological insulators
The increasing global power consumption of information and communication technology has driven exploration of low energy alternatives for the conventional transistor. Topological insulators (TIs) feature bulk gap protected dissipation-less surface conducting modes. Specifically, in the 2D TI, the dissipation-less surface conducting states near the Fermi level can be created/annihilated by using a suitable out-of-plane electric field, suggesting the possibility of realizing a perfect low energy switch. In this context, the proposed research represents an original and transformative approach by addressing the following objectives:
1. Analysis of different defects and defect-complexes in 2D TIs on a hBN substrate.
2. Investigate the effects of doping in 2D TIs to mitigate defect-induced Fermi level shifts and control bulk band gaps.
3. Study the effects of applied electric fields and strain on bulk band gaps and electronic transport in 2D TIs.
4. Develop an extensive material library for screening and optimizing promising engineered 2D TIs to support the experimental realization of low-energy electronic devices.
The topic will be studied through density functional theory (DFT) simulations using VASP and SIESTA, combined with tight binding (TB) modelling in Python and the NEGF method for simulating electronic transport with Kwant. Different phases of this proposed research will be arranged in work packages as follows:
WP-1: Modelling of formation energetics, electronic band structure and electronic transport in defective 2D TIs on a hBN subtrate
WP-2: Investigating the feasibility, stability, and electronic properties of doped 2D TIs in the presence of defects, and screening suitable doping species
WP-3: Modelling the effects of strain and applied electric fields on surface states and electronic transport
WP-4: Material library development
BITS Supervisor
Dr. Sayan Kanungo
RMIT Supervisor
Dr Jackson Smith
Other Supervisor BITS
Dr. Tanay Nag
Other Supervisor RMIT
Prof. Jared Cole
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Materials Engineering |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| PHYSICS |
| Physics, Condensed Matter Physics |
|
Defect Engineering in Semiconductor Photocatalysts for Enhanced Hydrogen Production
The primary aim of this study is to strategically engineer defects in semiconductor photocatalysts to enhance their performance for sustainable water-splitting applications. By introducing controlled structural imperfections such as lattice vacancies, foreign atom substitutions, and surface modifications, the objective is to optimize key photocatalytic properties, including light absorption, charge carrier separation, and reaction kinetics. The study seeks to establish a systematic approach to defect engineering that maximizes photocatalytic efficiency while minimizing undesirable recombination losses.
Methodology
To achieve this aim, various defect-inducing techniques will be employed, categorized into intrinsic and extrinsic methods:
Intrinsic Defect Engineering: Lattice vacancies (anion/cation) will be introduced via high-temperature annealing under controlled atmospheres. Ion bombardment and chemical treatments will induce strain, modifying the band structure.
Extrinsic Defect Engineering: Foreign atom doping via sol-gel and hydrothermal methods will enhance electronic properties. Heterojunctions with co-catalysts or secondary semiconductors will improve charge transfer and separation.
Defect Characterization: Spectroscopic techniques (PL, XPS) will identify and quantify defects. HR-TEM and SEM will analyze defect distribution and material integrity.
Water Splitting Experiments and Process Optimization: photocatalytic water splitting will be conducted for hydrogen evolution. Process parameters will be optimized for efficiency.
Objective
The primary objective of this research is to enhance semiconductor photocatalysts' efficiency through strategic defect engineering, enabling hydrogen production via solar-driven water splitting. Specific goals include:
? To prepare defective semiconductor materials by designing and incorporating tailored defect structures to enhance their photocatalytic properties.
? To optimize light absorption, charge carrier behaviour, and separation efficiency while minimizing recombination losses through strategic defect engineering and heterojunction formation.
? To characterize the defective semiconductor materials using spectroscopic, structural, morphological, and electrochemical techniques to understand defect distribution and their impact on material performance.
? To perform water-splitting experiments and optimize process parameters for efficient hydrogen production using defect-engineered semiconductor materials.
BITS Supervisor
SAROJ SUNDAR BARAL
RMIT Supervisor
Dr Ylias Sabri
Other Supervisor BITS
Mrunalini Kawaduji Gaydhane, Assistant Professor
Other Supervisor RMIT
Samuel Ippolito
Required discipline background of candidate
| Discipline |
| Chemical Engineering |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry |
| Environmental Engineering |
| Environmental Science and Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
AI and Data-Driven Computational Analysis of Human Dynamics in Sports: Athlete Performance Optimization, Injury Prevention, and Gender neutral coaching
This study aims to leverage AI/ML and Data Analytics to analyse human dynamics in sports, which is also extendable to healthcare for general population, and avoiding gender stereotyping in sports. The project will focus on athlete posture, motion optimization, injury prevention, and performance enhancement by integrating computational biomechanics, AI-driven movement analysis, and data science.
Biomechanical studies including optimization of posture and movement patterns is critical for improving athletic performance, reducing injury risks, and addressing gender-specific biomechanics in sports. Factors such as body structure, strength, intent, and external influences like aerodynamics and hydrodynamics significantly impact motion efficiency. This research will use CFD-based biomechanical simulations to assess airflow, resistance, and movement efficiency in sports such as cycling, swimming, and sprinting, where aerodynamics and hydrodynamics play a key role.
Additionally, AI-driven models will be developed for real-time motion tracking and predictive analytics, enabling personalized posture correction strategies. The study will incorporate gender-specific data analytics to explore variations in biomechanics and injury susceptibility, promoting equity in sports performance analysis and training protocols. Experimental validation will be conducted through sensor-based motion capture and AI-assisted injury risk prediction models, ensuring practical applications in athlete training, rehabilitation, and sports science research.
Methodology:
• Understanding human biomechanics and movement dynamics in selected sports disciplines using data science and AI-based analysis.
• Developing methodologies for posture and motion analysis using CFD simulations and AI/ML models.
• Integrating laboratory-based motion capture and sensor data collection to validate simulations and provide real-world movement insights.
• Design and implementation of AI/ML algorithms to identify inefficient movement patterns, predict injury risks, and recommend corrective actions.
• Experimental validation of AI-driven posture correction techniques using controlled studies
• Evaluation of AI-assisted training interventions for healthcare applications and gender nutrality
• Exploring applications in entertainment, such as virtual sports coaching, AI-based sports analytics for broadcasting, and immersive athlete training experiences using augmented reality (AR) and virtual reality (VR).
BITS Supervisor
Mani Sankar Dasgupta
RMIT Supervisor
Professor Firoz Alam
Required discipline background of candidate
| Discipline |
| Biomedical Science and Biotechnology |
| Computational Fluid Dynamics & Fluid Mechanics, Modelling |
| Health, Digital Health |
| Mechanical Engineering |
|
Development of surface-decorated lyotropic liquid crystalline drug delivery systems with various lipids/surfactants and optimization of their phase change behavior for superior wound healing application
Lyotropic liquid crystals (LLC) are self-assembled structures formed by amphiphilic molecules in water and exhibit various mesophases, such as lamellar, cubic, and hexagonal, depending on the lipid composition and water content. The application of LLCs in wound healing is emerging due to the unique properties of LLCs, which exhibit drug delivery, tissue engineering, bio-adhesion, and moisturization, as well as impart optimum viscoelastic properties for ease of application and spreading. In our work, we aim to develop hydrogel-based LLCs using various lipids and surfactants and study their phase-change behavior amenable for wound application. LLCs will be prepared using monoolein as a lipid, which can self-assemble into cubic, hexagonal, and lamellar phases, and surfactant, including poloxamers, span, tween, lecithin, and any PEGylated surfactants for surface decoration. The microfluidization technique will be used to prepare cubosomes and surface decoration will be executed to impart multifunctionality, including nanozyme incorporation and oxygen-release property by incorporating inorganic manganese oxide nanoparticles.
BITS Supervisor
Swati Biswas
RMIT Supervisor
Sampa Sarkar
Other Supervisor RMIT
Prof. Charlotte Conn
Required discipline background of candidate
| Discipline |
| Biological Engineering |
| Biological Sciences |
| Biomedical Sciences |
| Pharmaceautical Sciences, Pharmacology |
|
Deep Learning based Energy Management Strategies for Plug-in Hybrid Electric Vehicles
The IC Engine (ICE) based road transport sector contributes heavily to environmental degradation. To overcome this, Electric vehicles (EVs) are coming up as a solution. In pure EVs battery alone propel the vehicle and therefore requires a bulky battery pack. Due to absence of IC Engine (ICE), these vehicles have short driving range therefore, hybrid electric vehicles (HEVs) were conceptualized to bridge the power of ICE and the emission-free nature of EVs. Further to enable the charging of these HEVs externally, the plug-in HEVs (PHEVs) are going to be the future vehicles.
Involvement of two power sources makes the power management of hybrid power train complex. To take decision for switching on the battery or engine or both for optimum vehicle performance, is based on remaining charge in battery, demanded torque, drive distance and on the driving cycle. This motivates to design and develop deep-learning based control strategies to achieve optimum performance from the vehicle. The control ensures to avail a real–time update to the driver that when to turn on/off engine or battery. This research aims to develop power optimization strategies to improve energy efficiency and to optimize PHEV’s performance while considering thermal effect on battery. After a detailed literature survey, the followings objectives are identified:
1) Mathematical modelling of power train components: battery, ultra-capacitor power converters and electric motors
2) Design and development of adaptive charging and discharging algorithm for battery
3) Development of intelligent algorithms for Battery cell voltage balancing
4) Development of the deep learning based strategies for various Indian and Australian driving patterns in order to minimize the liquid fuel consumption and maximize the battery’s electrical energy
5) Validation of proposed strategy using real time simulator (Opal-RT/MicroLabBox) in complete vehicle environment using Battery Hardware in Loop (BHIL) platform.
Work Plan:
In first stage, the system will be designed/modeled and accordingly the components will be selected. The systems will be implemented in MATLAB/Simulink in second stage. In third stage, control algorithms will be tested in real –time In next stage, Cell balancing algorithms will be tested in real batteries available in the lab. In the last stage Validation of proposed strategy employing BHIL platform will be demonstrated.
BITS Supervisor
Professor HARI OM BANSAL
RMIT Supervisor
Dr Manoj Datta, Senior Lecturer
Other Supervisor RMIT
Dr. Kazi Hasan
Required discipline background of candidate
| Discipline |
| Data Science |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
|
2D heterostructures for gas sensing and catalytic applications
With the growing advancements in technology, manufacturing and living standards we see many environmental issues involving air pollutants of various categories. Detecting such gases effectively and selectively is a necessity for a clean and hazard free environment. The air pollutants can be categorized into inorganic, organic and acid gases. Many materials with varying dimensionality have been investigated for sensing of these toxic gasses including : carbon nanotubes, graphene, metal oxides, MXenes and heterostructured materials. Low dimensional and low-cost materials are preferable for such sensing devices. In this project we will design and study the sensing ability of a few 2D heterostructured materials based on MXenes and metal oxides/chalcogenides to detect specific gas pollutants from a first principles density functional theory (DFT) approach. Work will be done towards enhancing the sensing and catalytic ability of these designed materials by doping and functionalization; forming defects; applying strain and external fields. The study will extend towards converting some of these toxic gases into useful or harmless materials, thus cleaning the environment.
BITS Supervisor
Prof. Swastibrata Bhattacharyya
RMIT Supervisor
Prof. Michelle Spencer
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| ENGINEERING PHYSICS |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
| Physics, Condensed Matter Physics |
|
Advancing Smart Wearables using Machine Learning
The proposed project aims to enhance the capabilities of smart wearables through the integration of advanced machine learning (ML) techniques. Smart wearables such as fitness trackers and health monitors, have evolved significantly over the years. However, their potential to provide more personalized and intelligent insights into user health, performance, and behavior remains underexplored. This project seeks to address these limitations by leveraging machine learning models to improve predictive accuracy, real-time analysis, and adaptive responses of smart wearable devices. Aims: 1. Improve Accuracy of Health Monitoring: Current wearable devices provide basic metrics like heart rate, step count, or sleep patterns, but they lack in-depth analysis for detecting anomalies or predicting potential health risks. By utilizing machine learning algorithms, this project intends to enhance the wearables' ability to monitor complex health parameters such as stress levels, blood pressure variations, and early signs of chronic diseases. 2. Personalization of User Experience: Each individual’s health and activity patterns are unique. The project aims to develop intelligent algorithms that can tailor recommendations based on an individual’s specific data, including activity history, fitness goals, and health conditions. This will increase the relevance and effectiveness of feedback provided by the wearable device. 3. Real-time Decision Making: Machine learning models will enable wearables to process data in real-time, offering immediate insights into the user’s behavior, well-being, or performance. For instance, wearables can suggest exercise adjustments, alert users about irregularities in health metrics, or predict fatigue levels based on user patterns. 4. Predictive Analytics for Preventive Health: Through the use of ML models, we aim to create predictive tools within wearables to anticipate potential health issues (e.g., the likelihood of a heart attack or diabetic event), based on continuous monitoring of health indicators. This will move wearables from being reactive devices to proactive health management tools. Methodology: Data Collection; Model Development and Training; Integration with Wearables; Testing and Validation
BITS Supervisor
Navneet Gupta
RMIT Supervisor
Dr. Tu Le
Other Supervisor BITS
Meetha V Shenoy
Other Supervisor RMIT
Andy Song, Associate Professor
Required discipline background of candidate
| Discipline |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
|
Advanced Data Enabled Control of Hybrid Energy Systems through Unified Power Quality Controllers
Power quality concerns such as harmonics, low power factor and load unbalance are very common in power distribution system. Low power factor increases the utilization expenses while load unbalance leads to unwanted high neutral current and unreliable power supply. Utilization of non-linear loads including EVs is the main cause of harmonics, which affect system stability, create unwanted disturbance in the communication systems, malfunction of protective relaying systems and deficient power supply. Thus, harmonics elimination is of utmost importance and is realized using the filters. Unified power quality conditioners (UPQCs) are the powerful tools for maintaining power quality. UPQCs act as a shield against a wide-range of power quality threats, including voltage dips and surges, unwanted fluctuations, inefficient power utilization (reactive power), and uneven voltage distribution (imbalance).
Further, the demand for power is increasing continuously and renewable energy sources (RES) like solar and wind are being employed aggressively to address the same. As the penetration level of RES increases over time, the fluctuations like, voltage sags and frequency variations create serious power quality concerns. Moreover, the increasing penetration of EVs also adds further complexity in managing power quality issues in power grids. These challenges highlight the need for new data enabled and ML based techniques which will be utilized in this project.
Objectives: The main aim of this proposed RES-integrated UPQC is to minimize total harmonic distortion and to achieve constant DC-link voltage with better reactive power compensation over traditional methods. AI/ML-based algorithms will be developed to control UPQC. The system will be tested both in balanced as well as unbalance loading conditions. The developed system will be validated in real-time using hardware in loop methods employing MicroLabBox/OPAL RT and a lab prototype along with real time data
Methodology-System architecture: The boost converter will be connected with VSI, which is linked at the point of common coupling (PCC) with nonlinear/reactive loads. The three-phase grid-tied VSI has six insulated-gate bipolar transistors (IGBT) as switching devices and will behave as a power controller between DC-link and utility. Design and simulation of inverter topology will be carried out. Advanced AI/ML-based techniques will be developed to control the UPQC to improve the power quality
BITS Supervisor
Professor HARI OM BANSAL
RMIT Supervisor
Arash Vahidnia
Required discipline background of candidate
| Discipline |
| Electrical and Electronics Engineering, Power Engineering |
| Energy: Carbon Capture/Sequestration/Storage, Renewables |
|
Global Trade Disruptions: Enhancing Resilience and Sustainability in Supply Chain Management Using AI-Driven Analytics
The complexity of supply chains, coupled with global trade disruptions and geopolitical uncertainties, demands AI-driven modeling for resilient decision-making. Protectionist policies, like Trump 2.0 tariffs, increase volatility, costs, and cross-border logistics challenges. These challenges are particularly relevant for economies like India and Australia, which rely on stable trade relations with both the U.S. and China. India, a manufacturing hub and a critical player in global supply chains, faces risks from U.S. tariffs and market competition, while Australia, a key exporter of raw materials and agricultural goods, must navigate shifting trade alliances and supply chain vulnerabilities due to changing U.S.-China dynamics. This study integrates AI analytics, including fractional-order neural networks (FONNs) and Data Envelopment Analysis (DEA), to optimize efficiency, resource allocation, and benchmarking. By leveraging fractional calculus, DEA, and real-time AI analytics, the framework enhances resilience, sustainability, and adaptive decision-making amid global trade disruptions.
BITS Supervisor
Dr. Trilok Mathur
RMIT Supervisor
VIPUL JAIN
Other Supervisor BITS
Dr. Shivi Agarwal
Other Supervisor RMIT
Prof. Prem Chhetri, Professor
Required discipline background of candidate
| Discipline |
| Business Analytics |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science, Data Mining, Data Security & Data Engineering |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
|
Biodegradable Mulch films: A solution to 3 Cs Carbon sequestration,Crop and Climate Change
Aim: Design and development novel biodegradable mulch for agriculture.
Project focus is 'Sustainable Development and Environment', and it aligns closely with the 'Biotechnology for Sustainable Food Systems' theme. Overall, biodegradable, bio-compostable mulch film represents a practical application of biotechnology that supports environmentally sustainable practices in agriculture, helping to create resilient food systems that prioritize ecological balance, waste reduction, and resource efficiency.
Design and development of mulch films for agriculture, having to control weeds and moisture content along with property to act as bio-stimulant, would be advantageous. Seaweed is marine waste which has the advantage of growing easily and acts as source of carbon dioxide absorber, mitigating the climate change(1). As polymeric material, seaweed has the advantage of being biodegradable and the ability to be processed into films. In addition, seaweed have found to contain carbohydrates, amino acids, phytohormones necessary for the plant growth. As such, seaweed presents itself as the ideal material for production of mulch films(2). However, the mulch films made from seaweed alone suffer from poor mechanical properties and it has somewhat limited water barrier properties(3).
Management of waste from agriculture is also a challenge. Corn and cotton stalks are agricultural residues and contain lignin which can be extracted. Modification of seaweed mulch film by addition of lignin, has shown improvement in mechanical strength in polymer films along with UV resistance, antimicrobial, heat preservation& insulation from moisture and temperature fluctuation, can also improve soil quality, provide nutrients required for plant growth.
A biotechnological and sustainable use of biomass from marine and agricultural waste, to produce biodegradable mulch films with superior functional and bio stimulant properties which would aid in sustainable food systems to provide weed control and nutrients for crop growth is envisaged. Use of plant based raw material improves resource efficiency along with reduction in fossil fuel dependency, contributing to sustainable circular economy in agriculture. The proposal addresses three major environmental concerns: (i) waste management (ii) carbon footprint (iii) climate change.
Methodology: Seaweed/lignin film will be made using solvent casting as well as extrusion. FTIR, water absorption, HPLC will be done to characterize the mulch film.
BITS Supervisor
Purnima Doddipatla
RMIT Supervisor
Dr. Fugen Daver - Associate Professor
Other Supervisor BITS
Ramendra Pal,Dr.
Other Supervisor RMIT
Dr Ylias Sabri
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Engineering, Engineering Physics |
| Environmental Science and Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Geopolitical Risk and Green Energy Financing: A Comparative Analysis of India and Australia Using Machine Learning Techniques
1. Introduction: Many factors influence the transition to renewable energy, including geopolitical risks, policy frameworks, and financial investment dynamics. India and Australia provide contrasting but insightful case studies in green energy financing. India, a rapidly growing economy, is working to expand its renewable energy sector despite regulatory uncertainty and geopolitical challenges. Australia, which is endowed with vast renewable resources, is experiencing policy and market instability that is affecting green energy investments. Understanding how geopolitical risks affect financing decisions in these countries is critical to promoting sustainable energy development.
2. The study's objectives are as follows:
1) Assess the impact of geopolitical risks on green energy financing in India and Australia.
2) Compare the investment trends and policy frameworks that drive renewable energy funding in both countries.
3) Develop a machine learning-based risk assessment model to predict the influence of geopolitical factors on investment patterns.
4) Make policy recommendations to reduce risks and improve financial stability in the green energy sector.
3. Methodology:
Data collection includes geopolitical risk indicators (e.g. Global Risk Index, Political Stability Index). Green energy investment data from IEA, IMF, and national agencies. Macroeconomic and policy data sourced from government reports and financial institutions.
3.1. Machine Learning Approach: Random Forest and XGBoost are supervised learning models for risk prediction. Sentiment analysis of policy documents and news articles to gauge investor sentiment. Time-series forecasting (LSTM, ARIMA) can be used to model investment trends in response to geopolitical events.
3.2. Comparative Analysis: Comparing India's energy security challenges with Australia's policy-driven investment fluctuations. Identifying key geopolitical triggers that influence investment decisions.
BITS Supervisor
Aswini Kumar Mishra, Professor
RMIT Supervisor
Dr. Nirav Parikh, Senior Lecturer
Other Supervisor BITS
Prof. Rajorshi Sen Gupta, Associate Professor
Other Supervisor RMIT
Dr. Di Mo, Senior Lecturer
Required discipline background of candidate
| Discipline |
| Accounting |
| Banking, Finance and Economics |
| Business |
| Business Analytics |
| Data Science, Data Mining, Data Security & Data Engineering |
| Economics |
| Finance |
|
AI-powered Urban Flood Modeling for Climate Resilience and Risk Assessment and Insurance Implications
Urban flooding, driven by extreme rainfall, rapid urbanization, and inadequate drainage systems, poses significant economic and social challenges, including property damage, business disruptions, loss of productivity, traffic congestion, and increased health risks. From an insurance perspective, accurately estimating flood flow and assessing vulnerability is crucial for risk assessment, premium calculations, and policy development. Rainfall-runoff modeling is key in predicting flood events and mitigating potential losses. Establishing a robust mathematical relationship between rainfall and runoff is essential for insurers to refine flood risk models and optimize coverage plans. Additionally, climate change is exacerbating flood risks, leading to increased claims and financial liabilities for insurers. Integrating physics-based machine learning (PyML) and hybrid models (HyML - combining hydrological and ML approaches) offers a promising solution for improving flood predictions, enhancing risk assessment, and supporting more effective insurance strategies to safeguard urban communities. Keeping this in view, the present work aims to (i) Explore the effectiveness of PyML and HyML algorithms for historical streamflow analysis, focusing on enhancing flood risk assessment for insurance underwriting and policy pricing. (ii) Identify the most suitable flood prediction algorithms using the fuzzy Multicriteria decision-making (MCDM) technique and develop a stacking ensemble model based on top-performing algorithms (iii) Predict future streamflow under climate change scenarios using a suitable Global Climate Model (GCM) and Shared Socioeconomic Pathways (SSPs) to quantify evolving flood risks, (iv) Assess flood vulnerability in different future time segments and propose conservation measures for resilience-building. The proposed objectives will be demonstrated through case studies in India and Australia. The steps involved in the methodology are as follows: Literature Review, Data collection, comparative assessment, algorithm selection, stacking ensemble development, flood vulnerability assessment, Conservation Measures & Insurance Implications, Publications & Final Report.
BITS Supervisor
K Srinivasa Raju Senior Professor
RMIT Supervisor
Muhammed Bhuiyan Senior Lecturer
Other Supervisor BITS
Vasan Arunachalam
Other Supervisor RMIT
Vikram Garaniya
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
| Environmental Engineering |
|
Enhancing the Performance, Durability, and Sustainability of PDMS-Based Piezoresistive Sensors for Wearable Applications: A Rheological and Polymer Processing Approach
Flexible and stretchable Piezoresistive sensors based on Polydimethylsiloxane (PDMS) have become crucial for applications in wearable electronics, human motion tracking, soft robotics, and biomedical monitoring. PDMS is widely favored due to its bio- compatibility, flexibility, and ease of fabrication. However, several key limitations restrict the real-world applicability of PDMS-based sensors. These are as follows:
1.1 Limitations of PDMS based Sensors:
1. Durability and Long-Term Stability – PDMS exhibits creep and mechanical fatigue, leading to hysteresis and inconsistent sensor performance over time.
2. Sensitivity and Gauge Factor Limitations – Most PDMS-based sensors have a low gauge factor, making them inadequate for detecting small deformations.
3. Multifunctionality Constraints – Conventional designs only sense strain or pressure, while real-world applications demand multi-sensing capabilities (e.g., strain, pressure, temperature, and humidity).
4. Environmental Sustainability Issues – PDMS is non-biodegradable, contributing to electronic waste (e-waste), and sustainable alternatives remain underexplored.
5. IoT and Smart Integration Challenges – Existing PDMS-based sensors often lack real-time wireless transmission and AI-driven data analysis for smart applications.
To address these limitations, this study aims to explore the following research gaps:
1.2 Research Gaps
• The rheology and polymer processing effects on PDMS sensor durability.
• The impact of filler-polymer interactions on sensitivity and gauge factor improvements.
• The integration of biodegradable alternatives into PDMS-based composites.
• The design of IoT-compatible PDMS sensors with real-time data processing.
2. Aim of the Research
This PhD research aims to enhance the durability, sensitivity, multifunctionality, and sustainability of PDMS-based piezoresistive sensors by integrating rheological insights, polymer processing strategies, and creep analysis. The study will also explore biodegradable alternatives and IoT-based sensing solutions for next-generation wearable electronics.
BITS Supervisor
Sachin Waigaonkar, Professor
RMIT Supervisor
Everson Kandare ,Professor
Other Supervisor BITS
Tushar Sakorikar
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Predicting Mergers & Acquisitions in India and Australia: A Comparative Analysis using Machine Learning Approaches
1. Summary: A major financial activity that influences market consolidation and corporate growth is mergers and acquisitions (M&A). For investors, legislators, and business strategists, the capacity to forecast M&A events can yield important insights. This study seeks to develop a predictive model for mergers and acquisitions (M&A) in India and Australia utilizing machine learning techniques. The study aims to identify patterns and key determinants influencing M&A activity in both countries by analyzing historical financial data, economic indicators, and firm-specific attributes. A comparative analysis will elucidate the similarities and differences within the M&A landscape, assisting businesses, policymakers, and investors in making informed decisions.
2. Objectives:
To ascertain the principal financial and economic determinants affecting M&A activities in India and Australia.
To create a predictive model for mergers and acquisitions utilizing machine learning techniques.
To analyze and differentiate the M&A trends, regulatory frameworks, and economic circumstances in both nations.
To furnish actionable insights for corporate executives and investors.
3. Methodology
3.1. Data Collection: Historical mergers and acquisitions data sourced from financial databases (e.g., Bloomberg, Thomson Reuters, Capital IQ) and regulatory filings in India and Australia. Supplementary macroeconomic indicators will be obtained from governmental and financial entities.
3.2 Feature Selection and Engineering: Identifying pertinent financial ratios, stock performance metrics, firm characteristics, and macroeconomic variables for M&A prediction.
3.3 Machine Learning Models: Employing supervised learning methodologies including logistic regression, decision trees, random forests, and deep learning architectures (e.g., neural networks) to forecast M&A occurrences. The evaluation of model performance will utilize accuracy, precision-recall, and AUC-ROC metrics.
3.4 Comparative Analysis: Assessing disparities in M&A patterns between India and Australia through statistical tests and interpretability methods (e.g., SHAP values).
3.5 Validation and Testing: Employing cross-validation and back-testing with contemporary datasets to ascertain model robustness.
4. Expected Outcomes
Comparative insights into how financial, economic, and regulatory factors influence M&A differently in India and Australia.
Practical recommendations for investors, corporate strategists, and policymakers.
BITS Supervisor
Aswini Kumar Mishra, Professor
RMIT Supervisor
Dr. Nirav Parikh, Senior Lecturer
Other Supervisor BITS
Debasis Patnaik, Professor
Other Supervisor RMIT
Dr. Di Mo, Senior Lecturer
Required discipline background of candidate
| Discipline |
| Banking, Finance and Economics |
| Business |
| Business Analytics |
|
Moving Towards Enhanced Sustainable Transport by Improving Accessibility
Sustainable transport is a key priority in modern urban planning, and AI can play a crucial role in enhancing accessibility for all road users. AI-powered tools can help identify inefficiencies in transport networks, optimise multi-modal travel options, and ensure equitable access to public transportation, particularly for underserved communities. Predictive models can also assist policymakers in infrastructure planning by analysing demand patterns and environmental impacts, supporting the transition to greener mobility solutions.
This research integrates accessibility into active transportation modelling to enhance accessibility for cyclists and pedestrians. Different accessibility indexes are utilised to assess the relationship between accessibility and active transportation. The methodology involves a multi-step approach.
First, accessibility measures are computed based on transport network characteristics, including infrastructure connectivity, travel time, and land-use distribution. These indexes incorporate both proximity-based and network-based accessibility factors to reflect real-world travel conditions for pedestrians and cyclists as non-motorised transport users.
Second, the study employs spatial analysis techniques to evaluate the distribution of accessibility scores across different urban areas. A comparative analysis is conducted between accessibility measures and traditional land-use measures to assess their relevance in transport modelling. Statistical methods and AI techniques are applied to determine the extent to which accessibility influences active transport mode choices.
Finally, the findings are integrated into active transport modelling frameworks, providing insights for urban planners and policymakers. The results inform strategies to improve infrastructure and promote cycling and walking as viable transport options. By incorporating accessibility into active transport models, the study contributes to a more comprehensive understanding of mobility and supports the development of sustainable urban transport policies.
BITS Supervisor
Prof. Ajit Pratap Singh
RMIT Supervisor
Prof. Sara Moridpour
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Civil Engineering, Structural Engineering |
| Computer Science and Engineering/Computer Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
|
Development of Machine Learning-based Jamming and Spoofing Detection for GPS and NavIC Software Receivers
Global Navigation Satellite Systems (GNSS) are increasingly vulnerable to spoofing and jamming attacks, threatening critical applications such as autonomous navigation, IoT networks, smart grids, and telecommunications. To address these threats, this project aims to develop an advanced GNSS spoofing and jamming detection framework using Generative Adversarial Networks (GANs), Spiking Neural Networks (SNNs), and multi-antenna receiver techniques.
Unlike conventional classifiers (e.g., SVMs or CNNs), GANs will generate synthetic attack scenarios, enhancing model robustness by simulating adversarial spoofing and jamming signals. SNNs will be explored for their energy-efficient, neuromorphic capabilities, enabling low-latency real-time threat detection. Additionally, multi-antenna receiver techniques will be used to analyze spatial domain features such as Angle of Arrival (AoA) to distinguish authentic satellite signals from spoofed ones, strengthening resistance against sophisticated spoofing techniques like meaconing and coordinated attacks.
Beyond detection, reinforcement learning (RL) will be investigated for adaptive countermeasures, dynamically optimizing mitigation strategies such as beamforming, adaptive filtering, frequency hopping, and switching to inertial sensors based on real-time threat assessments.
The dataset will include publicly available repositories (e.g., Texbat), synthetic data from the Skydel GNSS simulator, and real-world RF signal recordings captured using an in-house GNSS software receiver (developed under the RESPOND grant). The ML-based detection algorithms will be integrated and tested with both this in-house receiver (developed for ISRO) and off-the-shelf commercial GNSS receivers to evaluate real-world applicability.
Performance will be assessed using classification metrics such as precision, recall, F1-score, confusion matrices, AoA estimation accuracy, and response time for adaptive countermeasures. The outcome will be a real-time, scalable GNSS security framework capable of detecting and mitigating evolving spoofing and jamming threats, ensuring GNSS integrity for UAVs, autonomous vehicles, and critical infrastructure protection.
BITS Supervisor
Nitin Sharma Associate Professor
RMIT Supervisor
Akram Hourani, Professor
Other Supervisor RMIT
Ke Wang, Associate Professor and Deputy Head of Department - R&I
Required discipline background of candidate
| Discipline |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Networks and Communications, Wireless Comms, Telecommunications |
| Neural Networks |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
Atomic-Level Insights into Lithium-Ion Intercalation in Silicon-Based Anodes: Simulations and Experiments of Composite Materials and Alloys for Enhanced Energy Storage Performance
Semiconductors are essential in various energy applications, including energy conversion, storage, and management, as well as in electric vehicles. Technologies like lithium-ion batteries (LIBs), solid-state batteries, and supercapacitors rely on semiconductors to enhance efficiency, longevity, and safety. Silicon is being explored as an anode material in LIBs due to its higher theoretical capacity compared to graphite. However, silicon faces challenges, including significant volume expansion during charge and discharge cycles, leading to degradation. To address this, the proposed project will focus on three key aspects:
1. Lithium-ion intercalation in silicon will involve investigating how lithium ions diffuse into silicon and how the lattice structure of silicon alters during cycling. Molecular simulations will provide insights into the mechanisms that govern the intercalation process.
2. Discovery of silicon-based composite materials, such as graphene and carbon nanotubes, that can buffer silicon's volume expansion, enhance electrical conductivity, and improve the overall performance and stability of the anode.
3. Exploration of silicon-based alloys, like silicon-germanium, to determine the best combinations that can better accommodate volume changes, enhance mechanical stability, and improve the cycling performance of silicon-based anodes in lithium-ion batteries.
Density Functional Theory (DFT) will be used to investigate how materials bond with silicon at the atomic level and how these interfaces can enhance the performance of the anode. The insight from the DFT will be used as input for Molecular Dynamics simulations to explore the diffusion dynamics of lithium ions inside the composite materials or alloys. The insights gained from these simulations will guide experimental work. For example, X-ray Diffraction can provide detailed information on the crystallographic structure of silicon, revealing how the lattice changes as lithium ions are inserted and removed during cycling. Additionally, electrochemical testing will allow for a direct comparison between experimental cycling data and the theoretical predictions from the simulations, enabling an assessment of how well the simulations match real-world electrochemical performance. This research aims to contribute to the development of more efficient, durable, and high-capacity anodes for lithium-ion batteries, driving advancements in energy storage technology.
BITS Supervisor
Pritam Kumar Jana
RMIT Supervisor
Dr Peter Sherrell
Required discipline background of candidate
| Discipline |
| Chemical Engineering |
| Chemistry |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Early Detection of Knee Osteoarthritis from MRI scans and clinical data using deep learning
Knee Osteoarthritis (OA) is the most common type of diagnosed osteoarthritis and is typically the result of wear and tear, and progressive loss of articular cartilage in the knee. Early detection of knee OA is important so that therapeutic approaches can be considered to halt
knee OA progression. Diagnosis of the disease is currently performed using X-ray and MRI that confirm and distinguish knee OA from other forms of arthritis. However, plain radiographs do not detect definite evidence of knee OA in the early stages because the bony changes on the radiograph only appear in advanced conditions. MRI scans, in comparison, have excellent tissue contrast, and distinct resolution on knee joints that could help in the early detection of the disease. This project aims to develop a novel deep learning model that would use MRI scans along with clinical information (demographic information, medical history, etc.) to perform early detection of knee osteoarthritis. The study will first implement open access databases to test the developed model and then implement it on the data collected from the hospitals who will be collaborators on this project. This would ensure that the developed model gets validated by clinicians and can be implemented in real world settings. The developed application has the potential to revolutionize detection and diagnosis of the most common type of osteoarthritis across the globe.
BITS Supervisor
Sougata Sen
RMIT Supervisor
Dr Priya Rani
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Biochemistry, Bioengineering, Biomaterials, Biotech, Biomed Eng/Sciences, Bioinformatics |
| Electrical and Electronics Engineering, Power Engineering |
| Health, Digital Health |
|
Multi-Suppliers Optimal vehicle routing models with diverse replenishment and Uncertainty
Vehicle routing models play an important role in optimising the logistics cost in the supply chains. There is a good amount of work that has been done on the formulation of vehicle routing models. However, when it comes to pickup of raw material supplies from different vendors with diverse supply frequencies to an OEM, or the delivery of finished goods to different distributors with diverse distribution frequencies from an OEM, the models are missing in the existing literature. However, it is the reality of the modern lean supply chains that the different suppliers may be required to furnish the raw material at diverse supply frequencies, and similarly in the downstream supply chain, different distributors may require to received the finished goods from the OEM at diverse replenishment frequencies. Also, many a times, there may be certain arcs that may not be useable because of road repair issues, and there may also be certain components that may have interdependence or incompatibility constraints. For example, two components may have irregular shapes that are incompatible with each other, and therefore, cannot be carried in the same trip. Similarly, there may be few components that must be carried in the same trip for nesting advantages, or kitting constraints, etc. The existing models also do not cover these practical realities.
BITS Supervisor
Prof. Gaurav Nagpal, Associate Professor
RMIT Supervisor
Prof. Prem Chhetri, Professor
Required discipline background of candidate
| Discipline |
| Business Analytics |
| MBA (Operations / Supply Chain and Logistics) |
|
Generative AI Agents for Research and Data Analysis
This project will develop a mult-agentic AI system leveraging Generative AI, Large Language Models (LLMs) and multi-modal learning to streamline the end-to-end research workflow for business professionals. The system will support the three core phases of professional research:
(1) Information Discovery and Synthesis: An intelligent Search Agent that performs comprehensive information gathering across multiple data sources, using advanced LLMs to understand context, evaluate relevance, and maintain source credibility while synthesizing information across multiple languages and formats.
(2) Data Analysis and Interpretation: An Analysis Agent that combines traditional statistical methods with state-of-the-art machine learning and Generative AI capabilities to process diverse data types, identify patterns and anomalies, generate predictive insights, and create dynamic visualizations.
(3) Content Creation and Presentation: A Writing Agent powered by the latest generative AI models that transforms analyzed data and insights into well-structured reports, presentations, and other business documents, adapting to industry-specific conventions while maintaining consistent narrative flow and professional tone.
These agents will seamlessly coordinate their activities while keeping human researchers in control of the process. The system will serve diverse business professionals (analysts, consultants, researchers, etc.) across sectors including Finance, Banking, Management Consulting, Market Intelligence, Business Strategy, and Economic Research.
Aims, Objectives and Methodology:
(1) Systematic review of AI tools, industry practices survey, user interviews for requirements, gap analysis, and development of evaluation criteria.
(2) Research and development of Search Agent (semantic search, cross-database synthesis), Analysis Agent (data preprocessing, multi-modal analysis), Writing Agent (NLG, citation management), Multi-Agent System capabilities, Human-AI collaboration framework.
(3) Evaluation and performance benchmarking of individual agent components as well as the multi-agent systems
(4) Pilot testing with select business professionals, Controlled experiments comparing AI-assisted vs. traditional research methods, Collection of quantitative metrics (time savings, accuracy, etc.), Qualitative feedback gathering through interviews and surveys, Usability testing and interface refinement
BITS Supervisor
Dr. Dhruv Kumar
RMIT Supervisor
Professor Mark Sanderson
Other Supervisor RMIT
Professor Falk Scholer
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computer Science/Information Technology |
| Computing: Collaborative and Social Computing, Computing Education, Computer Systems,Human Computer Interaction |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
|
Revolutionizing End-to-End Research Workflows for Scientific Discovery and Innovation Using Agentic AI
This research proposal aims to develop a human-centered AI collaboration system powered by advanced generative AI and autonomous AI agents that enhances and accelerates the scientific research lifecycle while keeping human researchers in control. We propose creating a comprehensive framework that empowers researchers through every stage from initial literature review to final publication, leveraging a human-in-the-loop approach for combining generative AI capabilities and human expertise. This collaborative platform will address current challenges in scientific research through specialized AI agents - including information overload in literature review, limited hypothesis exploration, experimental design optimization, data analysis bottlenecks, and research paper writing - all while ensuring that human researchers drive key decisions and maintain scientific rigor. We will focus on multiple domains including information technology, education, healthcare & biotechnology, advanced manufacturing & materials, food & agriculture, construction & infrastructure, and telecomms & cybersecurity.
Our core objectives span four key areas utilizing state-of-the-art generative AI: (1) Literature Analysis & Knowledge Synthesis, where we will develop autonomous AI agents (powered by generative AI) for comprehensive literature review, create knowledge graphs for gap identification, and implement trend analysis using large language models; (2) Hypothesis Generation, Validation & Experimental Design, focusing on generative AI agents for hypothesis generation and validation, cross-domain verification, experimental design optimization, and quality control frameworks; (3) Results Analysis & Validation, including specialized AI agents for data analysis pipelines, statistical validation, and automated error detection; and (4) Research Documentation & Communication, focusing on generative AI-assisted paper writing, and intelligent citation management tools powered by AI agents.
We will conduct extensive user studies with scientists and researchers across domains to understand their current AI adoption patterns, identify key opportunities for generative AI and autonomous agents, and co-design intuitive human-AI collaborative interfaces that seamlessly integrate into their research workflows. These studies will inform the development of tools that truly augment and enhance researchers' capabilities while addressing their specific needs and concerns around working with AI agents.
BITS Supervisor
Dr. Dhruv Kumar
RMIT Supervisor
Dr. Danula Hettiachchi
Other Supervisor RMIT
Dr. Estrid He
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computer Science/Information Technology |
| Computing: Collaborative and Social Computing, Computing Education, Computer Systems,Human Computer Interaction |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
|
Synthesis and design of porphyrin-based artificial photosynthetic antenna
This project aims to synthesize porphyrin-based metal-organic framework (MOF) semiconductor materials and to design artificial photosynthetic antennae for solar energy conversion devices. This type of material has several advantages over conventional semiconductor materials, such as crystalline Si and GaAs. First, the light absorption range and potential levels are tunable by altering a porphyrin periphery and center metal atom. The synthesis cost can be low, and the device is lightweight since most are composed of organic materials. Furthermore, this material can absorb almost all visible light with high extinction coefficients, and generated charge carriers have high mobilities and long charge-separated lifetimes. These superior optical and electronic properties are highly attractive to solar energy conversion devices.
The key objectives of this project are to:
Objective 1: Synthesize a series of metal porphyrin-based MOF structures
Objective 2: Characterise exciton and charge carrier dynamics
Objective 3: Design artificial photosynthetic antenna devices using the developed MOFs.
Methodology
Work package (WP) 1: Synthesis of a series of metal porphyrin-based MOF structures at BITS Pilani, Pilani Campus.
A series of metal porphyrins will be synthesized. With an appropriate bridging molecule, MOF structures will be formed. Subsequently, stacked MOF structures will be formed. These stacked MOF semiconductor materials will be characterized using XRD, XPS, SEM, and TEM technologies. Steady-state absorption and emission spectroscopies will be employed to monitor the optical properties of metal porphyrin, MOF, and stacked MOF structures.
Work package (WP) 2: Characterisation of exciton and charge carrier dynamics at RMIT
Dynamics of exciton states generated following light absorption and the generated charge carriers will be observed by broadband multi-time scale transient absorption and emission spectrometers and a time-resolved microwave conductivity system. The exciton state lifetimes, charge-separated state lifetimes, and charge carrier mobilities will be measured.
Work package (WP) 3: Development of artificial photosynthetic antenna devices prototype at BITS
An artificial photosynthetic antenna will be synthesized by attaching electron donor and acceptor molecules or co-catalysts to the developed MOF and stacked MOF. The most appropriate antenna structure will be identified by maximizing water-splitting reactions or CO2 reduction reactions.
BITS Supervisor
NITIKA GROVER Assistant Professor
RMIT Supervisor
Yasuhiro Tachibana; Professor
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials Chemistry |
|
AI and ML models for predicting the volume change behaviour of problematic soils
Problematic soils are frequently encountered worldwide. These soils usually have low bearing capacities and undergo significant volume changes when subjected to moisture variations. It is reported that damage caused by expansive soils exceeds $13.5 billion dollars annually to infrastructure. Chemical stabilization of these problematic soils is often employed to improve their engineering properties. Even though traditional calcium (Ca)-based stabilizers are used extensively, these treatment techniques are often found to be ineffective for sulfate-rich soils due to the formation of ettringite. Overall, expansive characteristics may be imparted due to clay mineral-induced swelling before chemical treatment and ettringite-induced swelling after the treatment of sulfate-rich soils with Ca-based stabilizers. Soil behaviour is complex; the physical, mechanical, and chemical behaviours significantly vary from one location to another, which is further altered by stabilization. The swelling characteristics of problematic soils depend on several parameters, including clay mineralogy, stabilizer type and dosage, sulfate content, and curing time before moisture intrusion. Currently, 1D free swell strain tests or swell pressure tests are performed to estimate the extent of swelling expected after moisture exposure. However, these tests are time-consuming and require a few weeks to obtain the swell strain or swell pressure data. Developments in AI and ML present an opportunity to analyze and model these swelling soils and predict the volume change characteristics as a function of the abovementioned causal factors. This will improve the reliability and accuracy of volume change prediction without the need to perform time-consuming laboratory tests.
This research project will identify and collate relevant datasets (untreated and stabilized soils) from published literature and comprehensive laboratory tests that will be conducted as a part of this study. Different problematic soils with various predominant clay minerals will be prepared and modified with gypsum to represent a wide range of sulfate levels. These soil groups will be treated with stabilizers. The swelling behaviour of the untreated and treated soils will be studied after various curing periods. ML and AI algorithms will be employed, and their suitability for predicting the volume change characteristics will be evaluated. Correlations will be captured to develop, train, and validate the prediction model.
BITS Supervisor
Dr. Sayantan Chakraborty
RMIT Supervisor
Dr Jaspreet Pooni
Other Supervisor RMIT
Dr. Dilan Robert
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
|
The Moderating Role of Gender and Institutions on Entrepreneurial Intentions: A Comparative Analysis of India and Australia using Explainable Artificial Intelligence (XAI) Approaches.
Summary: Entrepreneurship is widely regarded as a key driver of economic growth, innovation, and job creation. Both academic research and policy development require understanding what drives entrepreneurship. Personal traits, institutional support, and socio-cultural norms affect entrepreneurial intentions, which are the decision to start a business. Gender and institutional contexts moderate entrepreneurial intentions. This study uses Explainable Artificial Intelligence (XAI) methods to examine how gender and institutions affect entrepreneurial intentions in India and Australia.
1. Aims of the Proposal:
The project aims to examine how gender and institutional factors moderate entrepreneurial intentions in India and Australia. Since entrepreneurial intentions are cognitive precursors to entrepreneurial activity, they are essential to understanding and promoting entrepreneurship.
2. Research Questions and Objectives:
a) How do gender and institutional factors moderate the relationship between individual characteristics and entrepreneurial intentions in India and Australia?
b) What are the differences in entrepreneurial intentions between male and female individuals in India and Australia?
c) How do institutional factors such as government policies, access to finance, and cultural attitudes affect entrepreneurial intentions in these two countries?
d) How can Explainable Artificial Intelligence (XAI) techniques help to identify and explain the key drivers of entrepreneurial intentions?
2. Methodology:
This mixed-methods study will combine quantitative survey data with qualitative expert interviews and secondary data.
2.1 Data Collection:
Structured surveys of Indians and Australians will provide this study's primary data. The institutional context of both countries will be captured using secondary data from reports, government publications, and international indices (e.g., GEM, World Bank's Ease of Doing Business).
2.2 Data Analysis:
Descriptive Statistics: Calculating descriptive statistics to understand sample demographics is the first step.
Regression Analysis: The relationship between gender, institutional factors, and entrepreneurial intentions will be examined using multiple regression analysis. Moderating effects will be tested.
XAI Techniques: SHAP and LIME will be used to interpret regression models and identify the factors that most strongly influence entrepreneurial intentions.
BITS Supervisor
Aswini Kumar Mishra, Professor
RMIT Supervisor
Simon Feeny, Professor
Other Supervisor BITS
Debasis Patnaik, Professor
Other Supervisor RMIT
Dr. Nirav Parikh, Senior Lecturer
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Banking, Finance and Economics |
| Business Analytics |
| Computer Science/Information Technology |
|
Transforming Microbial-Derived Polyaminoacid into Sustainable Biopolymer Food Packaging Materials
The current food packaging industry heavily relies on petroleum-derived polymers, which pose significant environmental risks due to their limited reuse and recycling capabilities. Subsequently, there has been a shift in exploring bio-based, essentially plant-derived/ microbial-derived materials as sustainable alternatives for demanding food packaging applications. Despite numerous studies showcased the potential of bio-derived materials as effective substitutes, challenges such as compatibility issues with other materials, insufficient mechanical strength, and inadequate water resistance still exist. To address these, strategies including intra- and inter-crosslinking with biopolymers, incorporation of metal nanoparticles for antimicrobial properties, and the use of plasticizers and biodegradable polymer blends have been developed.
In view of these shortcomings, the current proposal aims to
1) Enhance the production of high molecular weight polyaminoacid, a biopolymer derived from thermophilic bacteria, through strategic media and process optimizations approaches.
2) To develop effective cross-linking techniques (intra/inter) and biopolymer (plant/microbial-derived) blending to transform polyaminoacid into packaging materials that comply with commercial quality standards.
3) To test the developed biopolymer-based packaging for its mechanical properties, compatibility, and performance to ensure it meets industry requirements for commercial use.
Biopolymer production will be investigated in shake flasks using cost-effective substrates, followed by stirred-tank bioreactor studies to optimize the processing conditions. The crude biopolymer will be subjected to purification through solvent precipitation and dia-filtration. Comprehensive testing of the properties will guide the selection of optimal cross-linking and blending methods to fabricate a robust biopolymer composite. Additionally, the biopolymeric material will undergo functionalization to enhance its suitability for advanced food packaging and protection applications.
BITS Supervisor
Vivek Rangarajan & Associate Professor
RMIT Supervisor
Mina Dokouhaki
Other Supervisor RMIT
Benu Adhikari
Required discipline background of candidate
| Discipline |
| Biological Engineering |
| Biotechnology |
| Chemical Engineering |
|
Understanding the molecular circuits of seed weight regulation in rice by interplay of hormones and metabolomes.
Amino acid transporters are membrane-localized carriers involved in the movement of amino acids from the source to sink tissues. They are important for various plants processes related to growth, development, and stress tolerance. Genetic manipulation of amino acid transporters can enhance stress tolerance and crop yield.Our prior data in Arabidopsis (Dhatterwal et al., 2021, 2022) showed that the AtAVT6 genes are strongly induced upon exogenous ABA treatment. Phytohormone abscisic acid (ABA) level rises when plants are exposed to abiotic stresses like drought, salinity, osmotic stresses and also during seed development (Sah et al., 2016), suggesting the abiotic stress-responsiveness of these transporter genes.Additionally, the expression pattern of AtAVT6 genes under nitrogen and sugar starvation conditions in ours as well as other reports indicate that the AtAVT6 members may have plausible roles in helping plants to survive nitrogen starvation conditions. Tissue specific expression analysis showed that the AtAVT6 genes are highly expressed in the senescent leaves. This indicates their involvement in the reallocation of released amino acids due to increased protein degradation in leaves undergoing senescence from source to the site of need, especially to developing sinks such as seeds and flowers. As a proof of concept we have demonstrated that overexpression of AtAVT6 family member has resulted in increased seed weight by twelve and twenty percent in two overexpressed lines of Arabidopsis (Dhatterwal et al., 2021, 2022). We intend to decipher the key genes responsible for the increased seed weight which can pave the way for future food security.
BITS Supervisor
Rajesh Mehrotra
RMIT Supervisor
Nitin Mantri
Required discipline background of candidate
| Discipline |
| Agriculture |
| Biological Sciences |
| Biotechnology |
| Genetics, Epigenetics, Genetic Engineering |
|
DigitOffshore: Smart Monitoring and Predictive Maintenance for Cost-Efficient Offshore Wind Foundations
The DigitOffshore project aims to develop a smart, cost-efficient monitoring and predictive maintenance framework for offshore wind turbine foundations. As offshore wind energy moves into deeper waters (>45m), traditional monopile foundations become impractical due to their excessive size, noise pollution, and environmental impact. Jacket foundations with suction buckets offer a sustainable alternative, but high design and maintenance costs present significant challenges. Current foundation designs depend on inaccurate seabed geotechnical estimations, leading to overdesign, inflated costs, and inefficiencies. While sensor data is collected, it is not effectively used for real-time design optimization or predictive maintenance.
Aims
This project aims to:
1. Optimize offshore wind foundation design by integrating real-time sensor data with Physics-Based Data-Driven (PDD) modeling to improve geotechnical parameter estimations.
2. Reduce overdesign and foundation costs by developing accurate computational models for jacket foundations with suction buckets in deep-water environments.
3. Enable predictive maintenance strategies to minimize operational disruptions and extend the lifespan of offshore wind foundations, focusing on on challenging seabed soils, including calcareous sands.
Methodology
1. Computational Modeling
o Development of advanced constitutive models to simulate the long-term cyclic behavior of jacket foundations with suction buckets.
o Integration of numerical simulations with real-time sensor data to update geotechnical estimations dynamically.
o Modular framework ensuring scalability across different offshore environments.
2. Data-Driven Methods
o Application of machine learning and data analytics to optimize 3D numerical simulations, reducing computational costs.
o Real-time analysis of sensor data (e.g., deformations, fatigue) to refine geotechnical design parameters and improve foundation accuracy.
o Development of predictive analytics models to enable proactive maintenance, reducing downtime and operational costs.
3. Experimental Testing and Validation
o Element testing on challenging seabed soils, including calcareous sands, to capture complex soil behavior.
o Direct shear and triaxial tests to investigate cyclic loading responses and stress-strain behavior under offshore conditions.
o Calibration of constitutive models and validation of numerical simulations using laboratory and field data for improved foundation performance predictions.
BITS Supervisor
Prof. Anasua GuhaRay
RMIT Supervisor
Dr. Dilan Robert
Other Supervisor BITS
Dr. Raghuram Ammavajjala
Other Supervisor RMIT
Mohammad Aminpour
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Civil Engineering, Structural Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
|
Data-driven Autonomous-Vehicle Integration in Logistics for achieving Net-Zero (DIAL-ZERO)
Climate change, global warming and increased greenhouse gas (GHG) emissions pose one of the most critical threats to the global population. The logistics sector (both inbound and outbound logistics) is responsible for 33% of global carbon dioxide. Both India and Australia are also witnessing massive surges in the logistics industry and subsequent increases in GHG emissions. In this regard, the “Net-Zero” emission concept, which aims at producing no additional emissions, has become a key player to address the climate change externalities, particularly in the logistics sector. Using decarbonising and sustainability techniques through green logistics approaches, such as the use of data-driven clean-vehicle technologies and the use of autonomous vehicles (AVs) in general, for inbound logistics in specific, can lead to a sustainable future. Autonomous vehicles like driverless truck technology in a supply chain in general and in inbound logistics can make the system sustainable. Autonomous vehicle technology can significantly reduce GHG emissions throughout the supply chain and can also ensure the complete supply chain is flexible, secure, resilient, cost-effective, faster, safer and energy-efficient to make the system less carbon-intensive, thereby helping the logistics sector contribute significantly towards net-zero. As both India and Australia have pledged to reduce their respective emissions by 45% by 2030 as per the Paris Agreement, there is a need to assess the existing system, evaluate the role of AVs on system performance in terms of environmental and energy efficiency, understand the willingness of relevant industries to adopt the system and formulate appropriate regulatory guidelines for implementation. In this context, the project aims to address the following objectives to be attained through a comprehensive methodology:
Understand the existing inbound logistics process and current decarbonization practices
Identify the strengths, weaknesses, and challenges associated with AV integration in the inbound logistics system through a focused group survey.
Design an efficient inbound logistics system with the introduction of AV technology by route, fleet and cost optimization and simulate various scenarios to identify best practices.
Evaluate the savings in greenhouse gas emissions, energy savings, and operational cost savings
Develop a dashboard indicating energy savings potential
Formulate guidelines and regulations for AV introduction
BITS Supervisor
BANDHAN BANDHU MAJUMDAR
RMIT Supervisor
Nirajan Shiwakoti
Other Supervisor BITS
Dr. Prasanta Kumar Sahu, Associate Professor
Other Supervisor RMIT
Peter Stasinopoulos
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
|
AI-driven Optimization of Limestone Calcined Clay Cement (LC3) with Bacterial Self-Healing Properties
The transition to sustainable and resilient construction materials is crucial to mitigating environmental impacts and enhancing infrastructure longevity. Cement production is one of the most carbon-intensive industries, with Ordinary Portland Cement (OPC) accounting for nearly 8% of global CO2 emissions. To address these environmental concerns, Limestone Calcined Clay Cement (LC3) has emerged as a viable alternative due to its lower carbon footprint, improved durability, and economic feasibility. LC3 reduces clinker content through the incorporation of limestone and calcined clay, significantly cutting down energy consumption and emissions.
Despite its advantages, concrete structures remain prone to cracking, which compromises durability and necessitates costly repairs. One of the most promising innovations in sustainable concrete technology is bacterial self-healing concrete, which employs microbial-induced calcium carbonate precipitation (MICP) to autonomously repair cracks, thereby extending service life and reducing maintenance needs. However, optimizing bacterial viability and self-healing efficiency within LC3 remains a challenge due to variations in hydration reactions, bacterial encapsulation techniques, and environmental exposure conditions.
To enhance the efficacy of bacterial self-healing in LC3, this project integrates Artificial Intelligence (AI) methodologies such as machine learning (ML) and computer vision, to optimize mix design, predict self-healing efficiency, and assess long-term sustainability. By leveraging AI-driven approaches, this research aims to develop a smart, adaptive, and eco-friendly LC3 system with superior self-repair capabilities, paving the way for a new generation of intelligent construction materials.
Research Objectives
1. AI-Based Mix Design Optimization:
2. Predictive Self-Healing Performance Modeling:
3. Automated Crack Detection and Healing Monitoring:
4. Enhancing Bacterial Viability and Performance:
5. AI-Driven Life Cycle Assessment (LCA) and Sustainability Evaluation:
BITS Supervisor
Dr. Mukund Lahoti
RMIT Supervisor
A/Prof. Srikanth Venkatesan
Other Supervisor BITS
Tejasvi Alladi
Other Supervisor RMIT
Dr. Lei Hou
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Civil Engineering, Structural Engineering |
| Computer Science |
| Construction Eng/Management and Materials |
|
Role of vacancies in indium-based nanomaterials sensitized with inorganic quantum dots
Indium sulfide nanomaterials have received considerable interest, as they can split water and generate hydrogen gas by absorbing the sunlight. However, one drawback of indium sulfide is that its bandgap is relatively large, and thus, only UV and blue parts of visible light can be utilized. Also, metal halide perovskite quantum dots (QDs) have attracted significant attention due to their bandgap energy tunability, high extinction coefficient, and long exciton lifetimes. However, they are unsuitable for generating hydrogen, although a sufficient amount of sun light can be absorbed.
This project aims to combine these two nanomaterials for efficient solar hydrogen evolution. Indium sulfide nanomaterials and metal halide perovskite QDs will be individually synthesized. Then by attaching the QDs on the surface of indium sulfide nanocrystals, the QD sensitised Indium Sulfide nanomaterials will be synthesized. Finally, it will be used as anode for water splitting reaction and at the cathode hydrogen gas will evolve.
The key objectives of this project are to:
Objective 1: Synthesize size and shape-controlled indium sulfide photocatalysts
Objective 2: Characterise perovskite QDs sensitized indium sulfide nanomaterials
Objective 3: Photoelectrochemical hydrogen evolution from QD sensitised indium sulfide
Methodology
Work package (WP) 1: Synthesis of size and shape controlled indium sulfide photocatalysts at BITS
Size and shape controlled indium sulfide nanomaterials will be synthesized. The synthesized semiconductor materials will be characterised by XRD, XPS, SEM and TEM. Steady state absorption and emission spectroscopies will be employed to monitor optical properties of the photocatalysts.
Work package (WP) 2: Characterisation of QDs sensitised indium sulfide nanomaterials at RMIT
The method to sensitise the indium sulfide nanomaterials with QDs will be investigated. QD exciton and an electron injection from the QD to the indium sulfide nanomaterials will be assessed by broad band multi-time scale transient absorption and emission spectrometers.
Work package (WP) 3: Solar hydrogen evolution at QD sensitized indium sulfide at BITS
Photoelectrochemical hydrogen evolution from QD-sensitized indium sulfide nanomaterials will be assessed. The most appropriate sensitized nanomaterial structure will be identified by maximizing solar hydrogen evolution quantum yields.
BITS Supervisor
Mrinmoyee Basu
RMIT Supervisor
Yasuhiro Tachibana; Professor
Required discipline background of candidate
| Discipline |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials Chemistry |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Resilient and Sustainable Urban Transport Infrastructure: A Data-Driven Approach for Vulnerable Road User Safety
The safety of Vulnerable Road Users (VRUs), including pedestrians, cyclists, and motorcyclists, is a critical concern in urban road networks, necessitating the integration of sustainable and resilient infrastructure. Sustainable infrastructure prioritizes environmentally friendly and efficient designs, while resilience ensures adaptability to changing urban conditions, extreme weather events, and increasing traffic demands. Implementing smart traffic management systems, pedestrian and cyclist-friendly intersections, and communication technologies can significantly enhance the safety of VRUs. In addition, data-driven approaches, such as AI-based predictive modeling and real-time monitoring, can help identify high-risk areas and optimize road safety measures. By combining sustainability, resilience, and technology-driven interventions, urban transport systems can be transformed into safer, more efficient, and more sustainable environments for all road users.
The project will adopt a multi-phase AI/ML and Data Science-driven approach with a mix of field data collection, computational modeling, and urban infrastructure design.
Phase 1: Data Collection & Analysis (Year 1)
• VRU Safety Data Acquisition.
o Collect traffic, road, socioeconomic, land use & weather data.
o Analyze historical crash datasets from transport agencies in India & Australia.
• Spatial and temporal Analysis for Hotspots:
o Identify high-risk pedestrian and cyclist zones using GeoAI and heatmaps.
Phase 2: AI Model Development & Infrastructure Integration (Year 2)
o Machine Learning-Based VRUs Behavioral Analysis.
o Develop AI models to predict VRU movement patterns, behavior, and vehicle interaction.
• AI-Powered Safety Predictions:
o Implement predictive models for crash severity and crash frequency of VRUs:
o Create AI-driven urban infrastructure simulations and Digital Twins for VRU safety enhancement.
Phase 3: Pilot Deployment & Smart Traffic System Integration (Years 3 and 4)
• AI-Based Smart Crosswalks & Traffic Signals:
o Deploy AI-driven adaptive signal control systems at high-risk intersections.
o Implement AI-integrated VRU alert systems using smart technologies.
• Real-World Testing & Policy Engagement and evaluating the impact of scenarios.
o Collaborate with urban planners, municipalities, and transport authorities in India & Australia to validate and test the safety scenarios.
This project will establish a global benchmark for AI-driven transportation safety solutions.
BITS Supervisor
Prof. Ajit Pratap Singh
RMIT Supervisor
Prof. Sara Moridpour
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Civil Engineering, Structural Engineering |
| Computer Science and Engineering/Computer Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
|
Mechanical Performance Evaluation of Hybrid Fiber-reinforced Polymer Nanocomposites: A Comprehensive Study on Failure and Impact Analysis
Project Summary
Hybrid composites have been acknowledged as contemporary materials for numerous engineering applications. They comprise two distinct kinds of high-strength fiber cushioned with a comparatively low-strength matrix to fulfil specific strength needs. In real time applications, composite laminates undergo a combination of load scenarios. Hence, the knowledge of first-ply failure strength, and failure modes become essential for the structural design optimisations. This research includes the fabrication of the hybrid composite laminates using vacuum-assisted resin transfer molding (VARTM) followed by characterization of the fabricated hybrid composites with and without nanomaterials. Initially, mechanical (tensile and flexural) performance of these materials will be studied by varying the nanomaterial content. Subsequently, composites with better mechanical properties are further selected for impact studies. As assessing the impact resistance of produced composites is essential to evaluate their durability under real-world conditions. Impact testing at low and high velocities are two independent techniques to evaluate materials performance at varying speeds. Finally, non-destructive testing (NDT) techniques such as acoustic emission techniques (AET) will be used to understand the weaker regions of the produced laminates and correlate the observations with the failure mechanisms of composites under various loading conditions.
Objectives of the Proposed Research
1.Understand the influence of nanomaterial reinforcement in enhancing the mechanical performance of hybrid composites through failure mechanisms.
2.Create novel reinforcement architectural strategies to withstand impact loads and resistance to crack propagation for improved impact strength and fracture toughness of composites.
3.Establish correlations between NDT of composites and the failure mechanisms under various loading conditions.
Keywords: Hybrid composite, Nanomaterials, Mechanical Characterization, Failure Analysis, Non-Destructive Testing.
Methodology:
1.Material Development using VARTM manufacturing process
2.Characterization and Testing of the fabricated composites
3.First ply failure of fabricated composites using acoustic emission testing
4.Impact testing of the fabricated composites
5.Validation and Simulation using ABAQUS.
BITS Supervisor
SHARAD SHRIVASTAVA ASSOCIATE PROFESSOR
RMIT Supervisor
RUSSELL VARLEY, PROFESSOR
Other Supervisor BITS
Arun Kumar Jalan
Other Supervisor RMIT
Srinivas Nunna
Required discipline background of candidate
| Discipline |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Development of graph-based computational tools for generating complex building layouts
In architectural design, floor planning is fundamental to shaping a building’s functionality, efficiency, and spatial quality. Floor plan design is a multi-constraint problem involving factors like site boundary conditions, room shape and size, adjacency requirements, fixed spatial elements, cardinal orientations, circulation efficiency, and accessibility standards. Traditionally, architects invest significant time manually sketching and refining layouts to achieve an optimal design. However, with the rising demand for residential and commercial developments in India and Australia, there is an increasing need for computational approaches that can streamline the design process while maintaining architectural integrity.
This project aims to develop graph-based algorithms, integrated with optimization tools, to generate architecturally viable and regulation-compliant commercial building layouts. The methodology will address the following aspects:
1. Finalizing the List of Inputs
Since floor plan generation is a multi-constraint problem, we define the following key parameters:
• Plot Boundary: The study focuses on rectangular and rectilinear plots to maintain practical applicability.
• Bubble Diagram: A structured representation of spatial relationships, required adjacencies and non-adjacencies, and the distinction between interior and exterior rooms.
• Room Sizes and Proportions: Defining room areas with preferable aspect ratios to ensure functional and aesthetically balanced layouts.
• Cardinal Orientation (Sunlight Optimization): Identifying optimal positioning for sun-facing spaces and corner rooms to enhance natural lighting, thermal comfort, and passive solar gains.
• Circulation and Access
2. Algorithm Development
The core of this project is the development of optimization-driven graph algorithms to automate floor plan generation. The approach will include:
• Positioning rooms within the plot boundary while minimizing wasted space and ensuring adherence to adjacency constraints.
• Embedding passive design principles such as cross-ventilation corridors and optimal window placements.
• Implementing rule-based filters to assess the feasibility of generated layouts
3. Validation and Iterative Refinement
To enhance the practical applicability of the generated layouts, we will conduct a validation phase involving expert feedback from architects, sustainability consultants, and energy assessors in both India and Australia.
BITS Supervisor
A/Prof Krishnendra Shekhawat
RMIT Supervisor
Prof Priya Rajagopalan
Required discipline background of candidate
| Discipline |
| Computer Science |
| Computer Science/Information Technology |
| Mathematical Science |
|
Use of Generative AI for Climate-Adaptive and Sustainable Agricultural Water Management
Agricultural water management faces challenges from climate variability, rising demand, and declining water quality. Conventional AI models, though effective, rely heavily on historical data and struggle to generalize under unseen climate scenarios. This study proposes a Generative AI-driven framework that integrates synthetic climate and water scenarios with remote sensing-based soil moisture and crop health to enhance real-time decision-making and irrigation optimization. Unlike traditional AI, Generative AI models complex, nonlinear interactions, dynamically filling data gaps and optimizing water allocation. The framework will integrate AI-driven hydrological and agricultural software (SWAT+, AquaCrop, DSSAT) with Generative AI models (e.g., GANs, VAEs) and remote sensing data (Sentinel-2, MODIS, Landsat) to simulate climate-driven water demand and supply. A multi-source database of climate, soil, hydrology, crops, and socio-economic data will support model training, providing growers with adaptive irrigation strategies for both expected and extreme climate conditions.
Objectives
1. Develop an intensive multi-source database for training Generative AI models, integrating climate, soil, hydrological, remote sensing, agronomic, and socio-economic data.
2. Develop a Generative AI framework for climate-adaptive water management, integrating remote sensing data for improved irrigation planning.
3. Utilize AI-driven hydrological models (e.g., SWAT+, AquaCrop) and satellite-based soil moisture and vegetation indices for real-time irrigation optimization.
4. Generate synthetic climate and crop water demand scenarios using Generative AI for future climate conditions.
5. Develop an AI-powered chatbot and mobile application for real-time farmer advisory, integrating remote sensing-based field-specific insights.
6. Assess the socio-economic and environmental benefits of AI-driven water management, focusing on water-use efficiency, crop productivity, and groundwater conservation.
Generative AI will enable adaptive, scenario-based water management, surpassing conventional AI limitations. Remote sensing ensures high-resolution insights, while a robust database enhances AI predictions. This project empowers farmers with AI-driven, satellite-enhanced tools for sustainable water use, food security, and climate resilience.
BITS Supervisor
Dr. Rallapalli Srinivas
RMIT Supervisor
Deepak Gautam
Other Supervisor BITS
Dr. Dhruv Kumar
Other Supervisor RMIT
Dr Debaditya Acharya
Required discipline background of candidate
| Discipline |
| Agriculture |
| Artificial Intelligence |
| Civil Engineering, Structural Engineering |
| Environmental Engineering |
| Environmental Science and Engineering |
| Geography, Geoinformatics, Geoscience |
|
Development of a Photocatalytic Fuel Cell for Wastewater Treatment and Sustainable Power Generation
The rapid industrialization and population growth have led to a significant increase in wastewater generation, posing severe environmental challenges. Conventional wastewater treatment methods are often energy-intensive and inefficient in removing persistent organic pollutants. To address this, Photocatalytic Fuel Cell (PFC) has emerged as a promising dual-function technology, capable of treating wastewater while simultaneously generating electricity. This research aims to develop an advanced PFC system by designing and synthesizing a high-performance photocatalyst for enhanced pollutant degradation and energy conversion efficiency. The project will focus on the fabrication and characterization of photoelectrodes and membrane electrode assemblies (MEA) to improve the cell performance. The PFC will be optimized for real-world wastewater treatment applications. Furthermore, a techno-economic and environmental feasibility assessment will be conducted to evaluate its potential for industrial-scale deployment. The proposed study is expected to contribute to the development of sustainable wastewater treatment solutions while harnessing wastewater as an energy resource, aligning with global efforts toward clean energy and environmental protection.
BITS Supervisor
Naveen Kumar Shrivastava
RMIT Supervisor
Dr Peter Sherrell
Other Supervisor BITS
Sanket Goel
Other Supervisor RMIT
Prof. Enrico Della Gaspera
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Nanotechnology, Nanomaterials, Nanomedicine, Nanoscience |
|
Waste to Energy: Harnessing Recycled Graphite from spent LiBs for Hydrogen Evolution Reactions
The horizon for lithium-ion battery (LIB) waste becoming a global problem is rapidly approaching. This project aims to develop an innovative upcycling strategy for LIB waste, turning recycled graphite into an electrocatalyst for the green hydrogen evolution reaction (HER).
Cheap, green HER technologies is critical for the decarbonisation of industry such as metal refining, and ammonia production, whilst also having use as a clean fuel or energy supply. Recycled graphite (accounting for 20% of battery mass), offers a promising alternative to expensive noble metal catalysts, due to its low cost, structural stability, and tunable surface chemistry.
The research will focus on recovering, processing, and functionalizing graphite to enhance its catalytic properties. Chemical, thermal, and electrochemical treatments will be explored to optimise surface and electronic properties for the HER.
The methodology includes:
1. Graphite Recovery & Processing: Purification of graphite obtained from waste LIBs (to be provided by industry partner).
2. Material Characterization: Structural, morphological, and electrochemical analysis using XRD, SEM, TEM, XPS, and Raman spectroscopy.
3. Electrocatalytic Testing: Evaluation of HER performance using potentiostatic and galvanostatic techniques in different electrolytes.
4. DFT Simulations: Computational studies will be performed to understand the catalytic mechanisms involved in the conversion of graphite into an electrocatalyst and its activity for HER. These simulations will help predict active sites, charge distribution, and reaction pathways.
5. Performance Optimization: Stability and reusability assessment for scalable hydrogen production.
This research supports clean energy transitions by utilizing recycled carbon materials for green HER. The findings will contribute to green hydrogen production, energy storage solutions, and circular economy practices, offering an eco-friendly and cost-effective alternative to conventional catalysts.
BITS Supervisor
Afkham Mir
RMIT Supervisor
Dr Peter Sherrell
Other Supervisor RMIT
Prof. Dan Liu
Required discipline background of candidate
| Discipline |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry or Chemical Sciences |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Development of AI/ML Models for Behaviour Prediction and Design Optimization in Next-Generation Sustainable Urban Infrastructure
(A) Aim: This research aims to develop advanced AI/ML models capable of predicting the structural behaviour of existing steel and composite structures while optimizing the design of future structures to achieve high performance, material efficiency, and sustainability. The AI/ML models will be trained to accurately predict the service life and performance of existing structures, addressing the urgent need for modern, sustainable construction practices. In designing new structures, the models will optimize material usage and structural configurations, leading to lightweight, resilient, and ductile structures. A key focus of this research is recyclability, with the proposed composite systems expected to considerably reduce the construction costs as well as the life cycle embodied energy compared to conventional structures. This study intends to establish a new benchmark in sustainable building practices by delivering an innovative and eco-friendly solution for urban infrastructure engineered to endure seismic events.
(B) Methodology:
(1) Development of a comprehensive literature review and database on steel and concrete composite built-up sections.
(2) Development of AI/ML Models for predicting the capacity and service life of steel and concrete composite built-up sections.
(3) Development of a numerical model of steel and concrete composite built-up sections.
(4) Validation of the numerical model against relevant available test results.
(5) Shape optimization to achieve high capacity and ductility steel elements.
(6) Experiments on novel optimized cold-rolled steel composite built-up beams.
(7) Parametric study & identifying the limiting values of critical parameters.
(8) Development of practical design guidelines.
(C) Aims of the proposed project are to:
(1) Develop AI/ML Models to accurately predict the capacity and design life of already built steel-&-composite structures.
(2) Compile the data set on cold-rolled steel concrete composite built-up beams.
(3) Develop lightweight green concrete.
(4) Develop a numerical model of cold-rolled steel concrete composite built-up beams.
(5) Develop an advanced shape optimisation method for cold-rolled components.
(6) Evaluate the performance of the newly developed, optimised cold-rolled steel composite built-up beams experimentally.
(7) Perform an exhaustive numerical parametric study by varying all the critical parameters.
(8) Develop practical design guidelines for adoption by International standards to use.
BITS Supervisor
Mohammad Adil Dar & Prof
RMIT Supervisor
Xiaodong Li & Professor
Other Supervisor BITS
Bahurudeen A & Prof
Required discipline background of candidate
| Discipline |
| Civil Engineering, Structural Engineering |
|
Study of residual stresses and microstructure development during the fabrication of light alloys
Additive manufacturing (AM) is a promising technique for fabricating medium- to large-scale light alloy components for automotive, aerospace, and biomedical applications. These AM processes include wire arc additive manufacturing, directed energy deposition, selective laser melting, and others. AM processes are often chosen due to their higher deposition rates, greater material usage efficiency, and lower costs. However, during these processes, residual stresses are generated because of the rapid heating and cooling thermal cycles. Residual stresses are a leading cause of component failure due to easy crack propagation and structural distortion. They have detrimental effects, such as reduced fatigue life and mechanical strength. The microstructures also exhibit large columnar grains, which result in lower strength and toughness. This study aims to establish a correlation between microstructural development and the role of residual stresses in fabricated light alloy components. The main research objectives are: 1) To fabricate light alloy components (such as aluminum or magnesium) using different AM techniques, 2) To establish a correlation between microstructural changes, defect formation, and residual stresses, 3) To investigate the effects of different AM processing parameters on residual stresses, and 4) To optimize AM processing parameters (e.g., travel speed, heat input, etc.) through numerical simulation.
BITS Supervisor
Dr Gulshan Kumar
RMIT Supervisor
Hua Qian Vivian Ang
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| Materials Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Metallurgical Engineering |
|
Developing Cyber Physical System for Machining in the Context of Industry 4.0/5.0
Cyber physical system (CPS) encapsulating new paradigm of industry 4.0/5.0 features is the deep fusion of physical components (machines, sensors, actuators) and cybernetics components (computer systems) with constant network connection and autonomous control. The cyber physical system is used to retrofit and upgrade traditional CNC machines into smart machines with the integration of various hardware and software components by enabling computation, communication, and control with real-time capabilities, modularity, reconfigurability and scalability. The major challenges in the implementation of a CPS system for the existing CNC machining platforms are the difficulties in integrating the heterogeneous networks, systems, and devices, and processing massive data. Although, distributed numerical control (DNC) helps to control multiple CNC machines by a central host computer in real time using modern network technology. But, the existing CNC machines are not smart enough to estimate either the power consumption or remaining useful life (RUL) of cutting tool before actual cutting. It limits the existing CNC machines to be a part of industry 4.0/5.0 due to lack of computation and control with real-time capabilities, modularity, reconfigurability and scalability. Therefore, an attempt is made to develop a cognitive cyber physical system for machining to monitor and control material removal processes, detect and diagnose faults, and optimize maintenance operations along with reduction of costs and enhancement of efficiency. The primary objectives of the present work are i) To develop a realistic energy prediction model to evaluate the distinctive energy demands of each toolpath during machining processes incorporating air cutting ii) To develop a cutting tool health management system for anomaly detection and estimating the remaining useful life (RUL) of the cutter through CPS for machining. In order to achieve the above mentioned objectives, an experimental setup consisting of dynamometer (KISTLER), power quality analyzer (HIOKI) in vertical machining center (VMC) is developed in the BITS central workshop. For measurement of workpiece surface integrity and cutting tool wear, various sophisticated instruments such as surface roughness tester, roundness tester, coordinate measurement machines, tool maker microscope which are available in metrology laboratory of BITS central workshop.
BITS Supervisor
Tufan Chandra Bera, Associate Professor
RMIT Supervisor
Songlin Ding, Professor
Required discipline background of candidate
| Discipline |
| Additive Manufacturing, Manufacturing, Automation |
| ME (Industrial/Production Engineering) |
| Mechanical Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
|
Development of a Novel Cathode Material for Enhanced Hydrogen Production in Microbial Electrolysis Cell
Microbial Electrolysis Cells (MECs) are promising bio electrochemical systems for sustainable hydrogen production from solid waste and wastewater. In MECs, electroactive bacteria decompose organic contaminants and electrons are transferred to the anode through extracellular electron transfer process and H+ diffuses to the cathode and produces H2 by receiving electrons. However, the efficiency of hydrogen evolution reaction is hindered by cathode limitations such as slow reaction kinetics, high overpotentials, and material degradation. Many catalysts have been explored in MEC with several advantages, for example, platinum-based cathodes offer high efficiency, though their high cost restricts widespread use. Cost-effective materials like stainless steel, nickel-based alloys, and carbon electrodes have been examined to increase the hydrogen evolution process efficiency. The limitations of hydrogen production can be overcome by developing catalyst of high intrinsic catalytic activity. As a solution to the challenges, the project focuses on developing a cathode with superior catalytic activity, lower over potential, and improved long-term stability. The developed cathode catalyst will be used for hydrogen production from organic substrates. By integrating machine learning (ML) and artificial intelligence (AI) in the process, the project aims to optimize material selection, synthesis, and operational parameters to improve hydrogen evolution efficiency in MECs, ensuring a cost-effective and scalable solution for sustainable energy production from wastewater. The major objectives of the project will be as follows:
a. Use of machine learning (ML) algorithms to predict optimal material compositions for synthesis of novel cathode materials with enhanced hydrogen evolution reaction
b. Optimize the synthesis process parameters using AI modeling and characterize the cathode material for electrochemical performance and stability
c. Optimize the operating parameters in a batch reactor using AI modeling and check the performance of the cathode in a continuous mode to understand the long-term stability and scalability
d. Identify the reaction intermediates and degradation pathways associated with hydrogen evolution on the developed cathode and use of AI-based kinetic modeling to optimize reaction conditions and predict long-term performance
BITS Supervisor
Dr. Pubali Mandal
RMIT Supervisor
Prof. Naba Kumar Dutta
Other Supervisor BITS
Dr. Abhradeep Majumder
Other Supervisor RMIT
Dr. Ravichandar Babarao
Required discipline background of candidate
| Discipline |
| Chemical Engineering |
| Civil Engineering, Structural Engineering |
| Data Science, Data Mining, Data Security & Data Engineering |
| Environmental Engineering |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Development of an Integrated Prefilter-AnMBR-PBR System for Sustainable Wastewater Treatment, Nutrient Recovery, and CO2 Utilization
The proposed research supports the United Nations Sustainable Development Goals (SDGs) by developing an integrated wastewater treatment system combining a prefilter, Anaerobic Membrane Bioreactor (AnMBR), and Photobioreactor (PBR) to enhance nutrient removal, CO2 utilization, and energy efficiency. Conventional treatment methods are energy-intensive (SDG 7) and inefficient in resource recovery, contributing to water scarcity (SDG 6) and climate change (SDG 13). This proposal reinforces BITS and RMIT's commitment to sustainability.
Key Features of the Prefilter-AnMBR-PBR System:
Enhanced AnMBR Efficiency: Prefiltering reduces membrane fouling and redirects organic-rich retentate to the AD reactor.
Energy Recovery: Biogas production offsets fossil fuel dependency (SDG 12).
CO2 Utilization: Microalgae in the PBR capture CO2 while removing nutrients, producing biomass for biofuels (SDG 9).
AI/ML-Driven Optimization: AI/ML techniques will improve efficiency, optimize process parameters.
Biogas Production Optimization: AI-driven analysis identifies optimal conditions for maximizing methane yield.
Microalgae Growth Monitoring: AI algorithms adjust parameters in real-time to enhance CO2 sequestration and nutrient removal.
Gap in the Knowledge
The impact of a prefilter on reducing membrane fouling while maintaining AnMBR efficiency remains unclear, affecting costs and energy demand. Similarly, optimising microalgae-driven CO2 sequestration for biogas upgrading requires further study. AI/ML applications in these areas are underutilized, presenting an opportunity for data-driven process optimization and predictive control.
Objectives
• Optimize membrane fouling control in AnMBR using AI/ML, ensuring improved biogas yield (SDG 7).
• Develop a self-sustaining wastewater treatment system with nutrient recovery (SDG 6).
• Utilize CO2 from biogas in PBR, improving methane purity while reducing CO2 (SDG 13).
• Implement AI/ML-driven process optimization, ensuring enhanced system performance.
Methodology
Phase 1: Wastewater characterization, prefilter optimization, and AI-driven predictive modeling for suspended solids reduction.
Phase 2: AnMBR design, fabrication, and AI-based operational control for biogas production and effluent quality improvement.
Phase 3: PBR integration with AI/ML-assisted microalgae monitoring for nutrient removal and CO2 sequestration.
Phase 4: Environmental and economic assessment, incorporating AI-based analysis for system sustainability.
BITS Supervisor
SAROJ SUNDAR BARAL
RMIT Supervisor
Maazuza Othman
Required discipline background of candidate
| Discipline |
| Biological Engineering |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Environmental Engineering |
| Environmental Science |
| Environmental Science and Engineering |
| MSc in Chemistry |
|
Enhancing Logistics Operations Through Soft Skills: A Strategic Path to Smart Workforce Development
In any competitive business, logistics professionals are the backbone for smooth operations. They tirelessly ensure a steady supply of fresh, high-quality ingredients which in turn effects performance in many dimensions such as optimising delivery schedules, reducing costs, and upholding customer satisfaction. As economies expand, industries experience higher demand, increased globalisation, and technological advancements, all of which demand a well-trained supply chain workforce. What makes these supply chain professionals so competent and successful that they deliver anything anywhere within the promised 10 minutes? The key skill sets relating to professionals may include communication and negotiation skills, leadership and decision-making, teamwork and collaboration, adaptability and problem-solving, and emotional intelligence for a business-centric mindset. The proposed study will explore the impact of various dimensions of soft skills on logistics performance, and the outcomes of the study will form the basis for developing a smart workforce. Both soft skill dimensions and relevant supply chain performance dimensions will be identified from secondary data sources through a literature review, and it will lead to the development of a structured questionnaire for surveys, interviews, and focus groups. The collected responses will be analysed empirically to study the impact of various soft skill dimensions on supply chain performance dimensions and the outcomes of this study will form the basis for developing smart workforce development. These approaches ensure a well-rounded understanding of skill gaps, industry expectations, and best practices. In a rapidly growing economy, logistics professionals must combine technical expertise with adequate soft skills to remain competitive and competent.
BITS Supervisor
Gajendra Singh Chauhan
RMIT Supervisor
Dr. Aswini Yadlapalli
Other Supervisor BITS
Professor Srikanta Routroy
Other Supervisor RMIT
Dr Vinh Thai , Professor
Required discipline background of candidate
| Discipline |
| Business |
| Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains |
|
Production of degradable-high tensile-nanoparticle enhanced-composite polymer films for food and agricultural applications.
The massive production and usage of non-biodegradable polymers as food containers had insurmountable detrimental effects on the environment and health of humans, plants and animals. This is because of the huge daily tonnage of single use plastics waste from food packaging. It will soon become necessary to move away completely from the production of such polymers. Biodegradable polymers (BPs) on the other hand have a number of advantages for protecting the environment. In applications like food packaging, the use of poly (butylene adipate-co-terephthalate) (PBAT) has huge potential. Polybutyrate, commonly known as poly (butylene adipate-co-terephthalate) (PBAT), is a semi-aromatic, biodegradable thermoplastic co-polyester that is simple to form and thermoform. PBAT and several other Biodegradable polymers are a suitable base for composite polymer films. The main goal is to develop degradable plastics with the maximum mechanical characteristics and degradability. It is already well known that Nanoparticles (NPs) enhance the strength of polymer films by acting as reinforcing agents within the polymer matrix, creating a network that effectively distributes stress and prevents crack propagation. As a result overall tensile strength, modulus, and impact resistance of the film is increased. The NPs act as tiny "reinforcements" that hinder the movement of polymer chains, leading to a more robust structure. By far, ZnO NPs and Carbon NPs have been the most researched NPs for enhancing the tensile strength of degradable polymer composites. There is a plethora of research still to be done in discovering new NPs for high-to-super tensile strength applications in food packaging. UV shielding, antioxidant and antibacterial activity are also a requirement in food packing. Hence, optimizing the film composition to deploy films for targeted applications in food packaging is the exciting field of research proposed here.
BITS Supervisor
Dr P C Sande
RMIT Supervisor
Associate Prof. Maggie Zhai
Required discipline background of candidate
| Discipline |
| Agriculture |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
Production of safe and degradable-antibacterial-nanoparticle enhanced-composite polymer films for biomedical applications.
Polylactic acid (PLA) is a biodegradable plastic made from renewable plant-based materials like corn, sugarcane, and cassava. Along with other biodegradable thermoplastics it is suitable for the production of thin degradable composite polymer films. It is already well known that Nanoparticles (NPs) enhance the strength of polymer films by acting as reinforcing agents within the polymer matrix, creating a network that effectively distributes stress and prevents crack propagation.
ZnO-Ag NPs are particularly advantageous because of their enhanced antimicrobial effects. There is a plethora of research that is yet to be accomplished in production of better and enhanced polymer strips for medical applications. We require materials that improve antibacterial properties by providing a medium to cover various surgical instruments.
Plastic films used as healing materials have wide application. These can potentially be designed with antioxidant properties which can organically heal wounds. Use of such products in postnatal care is absolutely vital. Hence there are several exciting biomedical applications of polymer composites enhanced with NPs, which we are proposing here for further research.
BITS Supervisor
Dr P C Sande
RMIT Supervisor
Associate Prof. Maggie Zhai
Required discipline background of candidate
| Discipline |
| Biomedical Science and Biotechnology |
| Chemical Engineering, Production Engineering, Thermal Eng, Separation Tech, Reaction Engineering, Powder and Particle Technology |
| Chemistry, Electrochemistry, Medicinal Chemistry, Coputational Chemistry, Colloids, Surface Chemistry, Catalysis |
| Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering |
|
DEFEND -- a digital twin enabled smart software prognostic platform for cyber-risk resilience, situational awareness and crisis management.
The proposed project aims to enhance the cybersecurity of computer-based systems by combining situational awareness capabilities with advanced device profiling techniques. This integrated approach addresses key gaps in current manual practices and provides a practitioner-friendly framework for detecting, assessing, and mitigating cyber risks. Technically the work is on building digital twin and using mathematical techniques for risk quantification. The proposed DEFEND software tool offers a groundbreaking solution that integrates Digital Twin Technology, Incident Response Mechanisms, and Device Profiling Techniques. This multi-dimensional approach not only provides real-time situational awareness and risk assessment but also enables practitioners to simulate and optimize responses to potential threats in both offline and online modes. Below, each core component is elaborated in detail: A. Digital Twin Technology: The digital twin forms the backbone of DEFEND by providing a virtual representation of safety-critical infrastructures. This technology facilitates real-time monitoring, simulation, and analysis of industrial systems, creating a sandbox environment for practitioners to explore various scenarios without impacting actual operations. B. Incident Response Mechanisms: Incident response is a critical aspect of mitigating the effects of cyberattacks or operational disruptions in real-time. DEFEND incorporates a dynamic crisis management module that enhances the practitioner's ability to respond to unfolding events swiftly and effectively. C. Device Profiling Techniques: Device profiling forms a crucial layer of defense in DEFEND, focusing on understanding the operational behavior of individual components to detect and mitigate threats effectively.
BITS Supervisor
Rajesh Kumar
RMIT Supervisor
Kandeepan Sithamparanathan
Other Supervisor RMIT
Malka N. Halgamuge
Required discipline background of candidate
| Discipline |
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Data Science, Data Mining, Data Security & Data Engineering |
| Information Technology |
| Networks and Communications, Wireless Comms, Telecommunications |
| Privacy, Private Policing and Security |
|
AI-Driven Underwater Robot for Detecting Submerged Plastic in Water Bodies
This project aims to develop an AI-driven underwater robot capable of detecting and mapping submerged plastic waste in water bodies. The increasing pollution of oceans, rivers, and lakes with plastic debris poses a significant environmental threat, affecting marine life and ecosystems. While surface-level plastic detection has seen advancements, identifying submerged plastics remains a challenge due to variations in depth, water clarity, and plastic degradation.
Aims:
1. Develop an autonomous underwater robot equipped with AI-based image recognition and sensor fusion techniques to detect and classify submerged plastic waste.
2. Enhance detection accuracy by integrating machine learning models trained on diverse underwater datasets, improving recognition under varying turbidity and lighting conditions.
3. Implement real-time mapping and localization, enabling effective tracking of detected plastic debris for targeted cleanup efforts.
4. Ensure adaptability for different aquatic environments, including freshwater and marine ecosystems, by optimizing hardware and software configurations.
Methodology:
• Hardware Development: The robot will feature an optimized propulsion system, depth sensors, high-resolution cameras, and sonar for efficient underwater navigation and plastic detection.
• AI & Computer Vision: Deep learning models, such as Convolutional Neural Networks (CNNs), will process underwater images to identify plastic waste. Sensor fusion will enhance detection accuracy by combining visual, sonar, and spectral data.
• Autonomous Navigation & Mapping: The system will integrate SLAM (Simultaneous Localization and Mapping) algorithms, enabling real-time mapping of detected plastics while navigating autonomously.
• Testing & Deployment: The prototype will undergo rigorous testing in controlled water environments, followed by real-world trials in lakes, rivers, and coastal regions to validate performance and adaptability.
This AI-driven underwater robot has the potential to significantly improve plastic waste detection and removal strategies, contributing to cleaner and healthier water ecosystems.
BITS Supervisor
Prasad Vinayak Patil
RMIT Supervisor
Professor Alireza Bab-Hadiashar
Required discipline background of candidate
| Discipline |
| Computer Vision, Image Processing, Virtual Reality |
| Electrical and Electronics Engineering, Power Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Robotics, Sensors, Signal Processing, Control Engineering |
|
BITS Supervisor
siddhi sharma
RMIT Supervisor
Tania Hogg
Required discipline background of candidate
| Discipline |
| Computational Fluid Dynamics & Fluid Mechanics, Modelling |
|
BITS Supervisor
siddhi sharma
RMIT Supervisor
Tania Hogg
Required discipline background of candidate
|