Search below for projects and apply. (Maximum of two projects)

Applications must be submitted by 24 April for the July 2024 intake.

The application is in 4 parts:

  • PART A - Project selection and Statement of Purpose (What is a SOP?)
  • PART B - Personal Details
  • PART C - Qualification Details
  • PART D - RMIT specific requirements
  • PART E - Document upload (Have your certificates and other relevant documents ready to upload)
For more information about the BITS RMIT PhD Program please visit this website.

Use the following search filters to find projects of interest

  • Search by the discipline dropdown. You can select multiple option
  • Enter the project number if you know it and press ‘search’
  • Enter a project keyword (I.e. thermodynamic) and press ‘search’

Minimum Qualification Requirements

Ensure you meet the requirements specified below before applying. Applications that do not provide evidence of meeting the minimum requirements will not progress further.

  • Master’s degree (MTech/ME/MPharm/MBA/MPhil, or equivalent with aggregate percentage of 65% or equivalent)*
  • GATE Score OR a high score in UGC-NET, CSIR, ICAR, ICMR, DST-INSPIRE**

*Where degree certificate or final year transcripts are not yet available, applicants may upload the previous semester / year transcripts

**Candidates without a valid GATE/ UGC-NET, CSIR, ICAR, ICMR, DST-INSPIRE score can be considered if they have undertaken GATE in the last five years AND/OR have a minimum of two years professional work experience, AND if they meet all other eligibility requirements. Where applicants wish to use the option of providing 2 years professional work experience as evidence – please include evidence within your uploaded documents


Select Discipline

Search by the discipline dropdown. You can select multiple options

Search Tool (example: 'thermodynamic' or 'BITSRMIT100036')

Enter the project number or project theme (i.e. thermodynamic) if you know it and press ‘search’

 

Total Projects Found: 136

PROJECT RESULT
BITSRMIT024B001236
Impact based Forecasting and Warning (IbFW) Services in Australia and India: Linking Weather Science with Society

Project Description

Early Warning Systems (EWS) are effective in mitigating disaster risk. Receiving a timely warning gives affected populations a chance to take appropriate protective actions. Recently, global meteorological communities have moved towards an evolving framework called ‘Impact based Forecast and Warning Services (IbFW)’. This framework emphasizes that early warning services, should be designed and developed from the perspective of the end users. It changes the focus from information availability to information utility. The importance of this comes from increasing risk from hydro-meteorological hazards in a changing climate and a realization that warning services require to be holistic and integrated. India Meteorological Department (IMD) and the Bureau of Meteorology (BoM), Australia, are fine-tuning IbFW in their respective countries using a multi-hazard approach. This project contributes to this goal focusing on the following aspects a) understanding public expectations from weather warning services, and b) effective communication of weather warnings. It will combine the two aspects together, synthesizing them through the theoretical underpinning and in data analysis. India and parts of Australia have similar climate vulnerability yet also have important differences such as cultural norms, infrastructural conditions, population size and concentration, and economic conditions. A study exploring evolution of IbFW’s structure, respective operational focus and the means through which user group linkages are being established will be useful in understanding how context shapes the success of IbFW in communicating weather and risk information. Methodology: This work will begin with a desktop study that compares the approaches taken to IbFW in the two countries, including an examination of the end products (i.e., the warnings and weather information) and the process used to produce and disseminate the warnings. Then a mixed-methods (interviews, focus groups and participant observation in the field), user-centred design approach will help to understand how context and user characteristics affect warning communication efficacy. The communication efficacy and the effects of the warning on intentions to take protective actions will be examined with a quantitative survey. A cross-cultural comparison provides the opportunity for each country to learn from the other about what works well, introducing new ideas to each country about how to craft effective warnings.

BITS Supervisor

Biswanath Dash

RMIT Supervisor

Amy Griffin

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Disaster Relief & Management
Geography, Geoinformatics, Geoscience
MA in Public Policy/Political Science/Sociology or similar
MA in Sustainable Development Practice
BITSRMIT024B001237
Blockchain-Enabled Solution for Medical Health Records

Project Description

The research project proposes a Blockchain-enabled solution for the integration of Medical Health Records (MHR). Healthcare information pertaining to patients’ data and transactions needs integrity, auditability, authenticity, scalability, and security features. The existing hospital information systems predominantly rely on cloud infrastructure managed by a single data provider, which exhibits multiple drawbacks, notably insufficient security protocols. Consequently, these weaknesses have resulted in numerous data breaches. The concentration of data in a centralized manner becomes a target for cyberattacks, which, in turn, gives rise to complications in maintaining a consistent patient data perspective across a network. Moreover, certain transactions demand a heightened emphasis on transparent and immutable record-keeping like procurement and shipping transactions within the supply chains of medical equipment and pharmaceuticals. Blockchain can offer cryptographic techniques to ensure data security, privacy and tamper-resistance. Blockchain can act as a standardised platform where data can be securely and efficiently exchanged between healthcare providers. Hence, the project will use the decentralized architecture of Blockchain that maintains distributed ledgers to achieve consistency, integrity, and authenticity of the transactions in the context of MHR. Specifically, the project aims to design a novel blockchain architecture for MHR management for diverse stakeholders by taking into account the issues of data security and heterogeneity. Access control is a crucial mechanism to ensure data security. Hence, the project will also focus on devising an access control mechanism that will allow individuals to allocate different permission levels with different granularities for the prevention of drug counterfeiting and medical/healthcare fraud.

BITS Supervisor

Prof. Subhrakanta Panda

RMIT Supervisor

Dr. Hai Dong

Other Supervisor BITS

Other Supervisor RMIT

Tabinda Sarwar

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
BITSRMIT024B001238
Development of nano-myco-membrane based integrated prototype for the treatment of real-time textile effluents

Project Description

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
BITSRMIT024B001239
Privacy-Preserving Authentication for IoT Devices using ZKP

Project Description

This project aims to enhance the security and privacy of Internet of Things (IoT) devices by conceptualising and developing a novel authentication framework. Utilising the advanced cryptographic technique of Zero-Knowledge Proofs (ZKP), the project seeks to enable IoT devices to authenticate each other and to central services securely without exposing sensitive information. This approach is designed to overcome the limitations of traditional authentication methods, which often compromise privacy or are vulnerable to various attacks. The project expects to generate new knowledge in the field of cybersecurity, specifically in the authentication of IoT devices, using the innovative approach of ZKP. This project is interdisciplinary, drawing on expertise from cryptography, computer science, and IoT technology, and utilising new techniques to ensure the privacy and security of IoT communications. By addressing the critical challenge of preserving privacy while maintaining robust security, the project will contribute to the development of safer, more reliable IoT ecosystems. This project should provide significant benefits, such as bolstering the security infrastructure of IoT networks, protecting user privacy, and fostering trust in IoT applications. By ensuring that IoT devices can authenticate in a manner that does not compromise sensitive information, the project supports the wider adoption of IoT technologies in sensitive areas, including healthcare, smart cities, and industrial automation. Ultimately, the successful implementation of this project's outcomes will lead to more secure, efficient, and privacy-compliant IoT ecosystems, benefiting society by enabling the safe and trustworthy use of these technologies.

BITS Supervisor

Amit Dua

RMIT Supervisor

Abebe Diro

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems
BITSRMIT024B001240
Access Control Framework for AI enabled Internet of Things

Project Description

This project aims to address the critical need for sophisticated access control mechanisms in AI-enabled Internet of Things (IoT) systems. With the exponential growth of IoT devices and the increasing integration of AI technologies, securing access to IoT systems has become more complex and essential. This project expects to develop new security access control framework by using an innovative approach that is interdisciplinary, combining insights from cybersecurity, artificial intelligence, and IoT technology. It aims to utilize new techniques in zero knowledge proofs, policy enforcement, and device authentication to develop a dynamic access control framework that adapts to changing contexts and threats. The successful development and implementation of this Access Control Framework should provide significant benefits, including strengthened security and privacy protections in IoT systems, enhanced user trust in IoT technologies, and the promotion of safer and more reliable IoT applications across various sectors. By addressing the complex challenges of access control in the context of AI and IoT, the project will contribute to the resilient and sustainable growth of the Internet of Things as a critical component of our digital future.

BITS Supervisor

Dr. Ashutosh Bhatia

RMIT Supervisor

Abebe Diro

Other Supervisor BITS

Prof. Kamlesh Tiwari

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Computer Science and Information Systems
Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems
Networks and Communications, Wireless Comms, Telecommunications
Privacy, Private Policing and Security
BITSRMIT024B001270
Adversarial deep learning in next best action marketing

Project Description

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

Other Supervisor RMIT

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
BITSRMIT024B001279
Membrane degradation and its mitigation strategies in low-temperature proton exchange membrane (PEM) fuel cells for light-duty electric vehicles

Project Description

Due to emergence of clean, green and digital electric mobility, there is huge demand of electro-chemical devices such as battery driven electric vehicle or proton exchange membrane (PEM) fuel cell driven electric vehicles. However, challenges such as high cost, declined electro-chemical performance and poor durability, are hindering the uptake of these technologies. PEM fuel cell driven electric vehicle has several advantages over battery driven electric vehicle such as cost, efficiency, operability and most importantly energy densities. However, the durability of components of PEM fuel cell such as membrane, electro-catalyst, bipolar plates are on of major challenges in PEM fuel cell. Therefore, understanding the degradation behavior and its mechanism in advanced functional materials such as proton conducting membrane followed by its mitigation is a crucial step to enhance the stability of PEM fuel cells. The detailed investigations were carried out to identify the electro-chemical, physical and process parameters causing membrane degradation under real time operation of PEMFC. The membrane thinning, pin-hole formation, cracks formation, polymer backbone detachment and peroxide radical attacks are some of factors causing membrane degradation and affecting PEMFC performance. The proposed project focuses on mitigating PEM degradation through in depth exploration of key degradation factors. This approach involves implication of advanced mitigation strategies such as PEM material enhancements, optimization of operating parameters and implementation of innovative methodologies. The aim of this study is not only to identify but actively address chemical, mechanical and thermal degradation factors for PEM. The essence lies in translating these mitigation efforts in to perceptible improvements, enhancing the overall stability and lifespan of PEM fuel cells performing under typical loads profiles of heavy duty vehicles. This, in turn, will significantly contribute to viability of PEM fuel cells within the realm of clean and green electric mobility solutions. 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

Other Supervisor RMIT

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
BITSRMIT024B001300
Designing circular supply chains for manufacturing firms

Project Description

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, prioritise minimising raw material use, extending product durability, and maximising recycling and reuse at the end of a product's life. This approach replaces the conventional ‘end-of-life’ business model with a more sustainable one, emphasising reusing, recycling, reducing, and recovering resources. This research project aims to design 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 implement circularity in their supply chains. The research will delve into the intra and inter-organisational capabilities and institutional factors that interact to achieve a circular supply chain. The study will unfold in three phases. The first phase will encompass a comprehensive literature review to gain insights into the capabilities and factors that facilitate circular supply chains. The second phase will involve gathering qualitative data from manufacturing firms to understand how these identified factors operate in real-world scenarios. Drawing on the insights from Phases 1 and 2, the research will develop a model with hypotheses to illustrate the mechanisms involved in achieving circular supply chains. Finally, a large-scale survey will be conducted to test and validate the model, ensuring its applicability across diverse manufacturing sectors. This multi-phase, multi-methodology study aligns with the United Nations' Sustainable Development Goals, in particular Goal 12 (Responsible Consumption and Production) and Goal 9 (Industry, Innovation and Infrastructure). By incorporating the principles of narrowing, slowing, and closing in sourcing, manufacturing, and recycling, the research aims to guide manufacturing firms in designing circular supply chains to foster a regenerative approach to sustainability.

BITS Supervisor

RAJESH MATAI

RMIT Supervisor

Priyabrata Chowdhury

Other Supervisor BITS

Other Supervisor RMIT

Kwok Hung Lau

Required discipline background of candidate

Discipline
Climate
MBA (Operations / Supply Chain and Logistics)
ME (Industrial/Production Engineering)
Sustainable Development, Development Studies, Development Geography, International Development
BITSRMIT024B001366
Vision Transformer based Deep Learning Architectures for Early Detection of Breast Cancer

Project Description

Every year, 1.38 million cases of breast cancer are diagnosed in India. Of these, 0.45 million people succumb to the disease, giving a mortality rate of about 33%. This means about 1 in 3 die due to breast cancer in India which is an unacceptably high number. Breast Cancer is also the most common cancer in the United Arab Emirates (UAE), with a majority of cases characteristically occurring in women younger than 50 years. Further, Breast Cancer is the most commonly diagnosed cancer for females in Australia. It is estimated there will be around 20,500 breast cancer cases diagnosed in females in 2023. This is around 28% of the estimated cancers diagnosed in females. Breast Cancer is normally diagnosed using physical examination followed by mammogram, Ultrasound and MRI Imaging. While Mammogram involves radiation and MRI is not generally favored by the patients, Ultrasound is simple, elegant and causes no discomfort to the patients. In this work, teams from Australia, UAE and India will work on applying Deep Learning techniques to Ultrasound Images to detect the presence and spread of tumors that characterize the breast cancer. Where available, Mammograms and MRI images will also be used to support the inferences drawn. While a majority of work reported in this domain focused on popular Convolution Neural Networks, literature is scant when it comes to applying Vision Transformers (VTs). In this work, we will focus on applying Vision Transformers for breast tumor detection. As is well known, VTs are quickly becoming the de-facto architecture for Computer Vision but very little is understood about how they work and what they learn. Further, while existing studies visually analyze the mechanisms of CNNs, the same is not widely reported for the VTs. In this work, the team will focus on both understanding and visualizing the functioning of VTs as applied to breast tumor detection. It will work closely with a Breast Cancer Specialist Doctor based in Muscat, Oman whose experience will be built into the VT models as a prior knowledge during training which might help in its early detection.

BITS Supervisor

M B Srinivas, Professor

RMIT Supervisor

Shaun Cloherty

Other Supervisor BITS

SWARNALATHA RAJAGURU

Other Supervisor RMIT

Dr Priya Rani

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
BITSRMIT024B001367
AI-Driven Disease Marker Discovery in High-Dimensional Genomic data

Project Description

This study will investigate the potential of AI-based methods to predict disease-associated markers from high-dimensional genomics data, focusing on SARS-CoV-2 infection severity as a prime example. RNA-Seq gene expression datasets from public repositories like the Gene Expression Omnibus (GEO) and ArrayExpress. The proposed dataset encompasses human studies on PBMC response to SARS-CoV-2 infection, ranging from healthy individuals to those with mild, moderate, and severe COVID-19 presentations based on well-defined clinical parameters. The datasets contain the expression data of around 20000 variables (genes) from across 2000 individuals. Genome-level datasets for omics analysis result in training data sequences and structures suitable for machine learning and deep learning. Emerging AI paradigms like Generative AI, Explainable AI, Hybrid AI, and Responsible AI will be investigated in this research. Explorations into the systems' theoretic dependence between randomization in feature perturbations and generalizability in blackbox optimizations of the deep neural network architectures lead to new theories for allied machine learning. Proper quantification of the hypothesis set in deep learning leads to various functional problems, oracular problems, sampling tasks, and optimization problems. Learning theories based on information theory, optimization theory, and game theory for data fusion will be investigated. This project aims to develop scalable, low-cost, sustainable, secure, and replicable technology by the development of low-cost Internet-of-Things-based continuous health monitoring, real-time analytics and alerts for preventive and predictive care with advanced AI systems. From the AI deployment side, the goal is oriented towards data repositories, feature engineering, data science microservices, etc. to express the application scenario, dataset, model, etc.

BITS Supervisor

Dr. Aneesh Chivukula

RMIT Supervisor

Du Yong Kim

Other Supervisor BITS

Dr. Jabez Christopher

Other Supervisor RMIT

Dr Priya Rani

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
Health, Digital Health
BITSRMIT024B001369
Machine Learning-Based Indoor Robot Localization and Mapping for Mobile Manipulator for Industrial Applications

Project Description

Aim: To create a VR based digital twin of Robots that can be used for various industrial applications. The localization of autonomous robots has been an active research area since the advent of Industry 4.0. Several applications in the industry include warehouse management, advanced manufacturing and elderly care. Localization in indoor environments becomes challenging, especially in the absence of the Global Navigation Satellite System and obstacles. The existing systems rely on various low-cost, miniaturized sensors like IMU, camera, LiDAR and UWB devices to perform precise indoor localization. Recent works have focused on using machine learning approaches for sensor fusion; improvements are still needed in terms of data quality, overfitting or underfitting, scalability and reliability. In this proposal, we propose to develop approaches for intelligent scene understanding using computer vision and perform multi-modal sensor data fusion using deep learning approaches, such as transformers, particle-based, and conventional methods. The focus of the work will be two folds: real-time operation and robustness for industry applications. We also propose to explore the application of inexpensive LiDAR line scanners for obstacle avoidance. The system will be tested in indoor environments like the construction industry or shopping malls, and experimental validation will be performed using mobile robots and mobile manipulators. The project will contribute to advancing scientific knowledge in sensor fusion and autonomous robot navigation, in addition to creating a prototype for deployment in the industry. Virtual reality and Digital twins will be used for simulation and for human-machine collaboration.

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
BITSRMIT024B001211
Corporate social responsibility (CSR), climate risk and sustainable firm performance in India: The role of green innovation and corporate governance

Project Description

This study delves into the complex interrelationships among Corporate Social Responsibility (CSR) practices, climate risk, green innovation, corporate governance, and sustainable 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 CSR considerations into business operations using robust panel data econometric models to control for industry and time effects as well as the potential endogeneity issues. Moreover, it emphasizes the necessity of a comprehensive approach to corporate sustainability through climate risk measures. 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 green innovation and corporate governance on the relationship between CSR practices and firm performance. It investigates how the green initiatives of the firm 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 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 CSR and public relations associated with diversity on boards and green initiatives.

BITS Supervisor

R. L. MANOGNA

RMIT Supervisor

Dr. Armin Pourkhanali

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Banking, Finance and Economics
Climate
Economics
Finance
BITSRMIT024B001216
Isolation and characterization of bioactive compounds from mangrove plants for antimicrobial resistant pathogens

Project Description

Bacterial antimicrobial resistance (AMR), is an urgent global public health threat, killing at least 1.27 million people worldwide and associated with nearly 5 million deaths. The six leading pathogens for deaths associated with resistance are Escherichia coli, Staphylococcus aureus, Klebsiella pneumoniae, Streptococcus pneumoniae, Acinetobacter baumannii, and Pseudomonas aeruginosa. There are very few effective drugs to treat multidrug-resistant infections caused due to these pathogens, which represent the main threat at present. Mangrove plants thrive under extreme environment which lead to the development of special metabolic pathways to produce unique compounds that enable them to tolerate stressful environmental conditions. Mangrove species have various applications in folk medicine. Mangrove plants are a rich source of steroids, triterpenes, saponins, flavonoids, alkaloids and tannins. Extracts from different mangrove plants are reported to possess diverse medicinal properties such as antibacterial, antifungal, antihelminthic etc. Due to side effects of existing chemotherapeutic agent and the resistance developed, plant derived compounds have received much attention as a potential source of the future drug. Goa state is located in western coast of India and mangrove vegetation occupies 500 hectares of its area. Goa represents 17 mangrove species that include 14 true and 3 associated species. Australian mangrove forests comprise 45 species across 18 families, which is more than half of the world's total mangrove species. It has been already reported that among them several mangrove species produce bioactive compounds that may control microbial growth. Therefore, an attempt would be made towards isolation of antimicrobial compounds from the bestowed mangrove flora of Goa and Australia. Leaves of mangrove species will be tested against AMR pathogenic bacterial strains, and novel compounds from the identified mangrove species will be isolated, identified and functionally characterized. Aims: 1. Identification of potential mangrove species for their antimicrobial properties against AMR pathogens 2. Isolation and identification of novel antimicrobial compounds from mangrove species 3. Structural and functional characterization of identified molecules isolated from mangrove plant species Methodology: • Collection and extraction of plant material: Leaves of mangrove species of Goa will be collected from the estuarine complex of Mandovi and Zuari river. Man

BITS Supervisor

Kundan Kumar

RMIT Supervisor

Nitin Mantri

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Biological Sciences
Biotechnology
Chemistry or Chemical Sciences
BITSRMIT024B001220
Diversity, Equity, and Inclusion (DEI) in Global Supply Chains

Project Description

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

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Business
Mathematical Sciences, Operations Reserarch, Decision Sciences, Transportation Engineering, Supply Chains
MBA (Operations / Supply Chain and Logistics)
BITSRMIT024B001234
Design and development of efficient self-powered, solar blind photodetectors based on 2D materials and Ga2O3 heterojunctions

Project Description

Electromagnetic waves of below 280 nm wavelength are considered solar-blind or UV-C region (200-280 nm) and it has plenty of applications in military, secured space communications, and safety monitoring. Ultra-wideband gap semiconductors such as Ga2O3 emerged as the most natural choice for solar-blind photodetectors (SBPD) due to its high bandgap. The high radiation hardness of Ga2O3 makes it suitable in harsh environments such as space applications. On the other hand, 2D materials are always a preferred choice for those applications where large and highly reactive surface area is required. For current generation SBPD, there exists a trade-off between two key parameters-responsivity and response time. For successful commercialization of SBPD, desired response time should be smaller than 1 µs whereas responsivity should be greater than 1000 AW-1, simultaneously. This project will aim to achieve the above-mentioned responsivity and response speed by realizing the heterojunction of 2D materials with Ga2O3. To ease the fabrication and minimize the experimental optimization load, firstly we will do materials modeling using DFT and the anticipated results would be a comprehensive understanding of the electronic structure, density of states, defect generation, propagation, and relaxation mechanism in 2D materials, Ga2O3, and their heterostructures. Thereafter, optimized materials will be simulated by a multi-physics model to optimize the heterojunction to demonstrate fast response and high responsivity as required for the commercialization of this technology. Subsequently, the optimized heterojunction will be fabricated to demonstrate excellent responsivity and a response time as required for the commercialization of this technology.

BITS Supervisor

Prof. Satyendra Kumar Mourya

RMIT Supervisor

A/Prof. Enrico Della Gaspera

Other Supervisor BITS

Professor RAHUL KUMAR

Other Supervisor RMIT

Professor Sumeet Walia

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
BITSRMIT024B001244
Anomaly Detection in IoT Data Streams

Project Description

This project aims to investigate and implement advanced anomaly detection algorithms in IoT data streams. By utilizing cutting-edge machine learning and statistical analysis techniques, the project seeks to identify unusual patterns, behaviours, and potential security threats within massive datasets generated by IoT devices. The proliferation of IoT devices across various sectors, including healthcare, manufacturing, and smart cities, generates vast amounts of data continuously. This project expects to generate new knowledge in the area of anomaly detection by using an innovative approach that is interdisciplinary, utilizing new techniques in machine learning, data science, and cybersecurity. It addresses the critical need for real-time monitoring and analysis to ensure the integrity, security, and reliability of IoT systems. This project should provide significant benefits, such as improving the security posture of IoT networks, reducing the risk of data breaches and system compromises, and enhancing the trustworthiness of IoT devices and data. Additionally, by facilitating the early detection of anomalies, the project can help in preemptive problem-solving, thereby minimizing potential damages and ensuring the continuous and reliable operation of IoT systems.

BITS Supervisor

Dr. Ashutosh Bhatia

RMIT Supervisor

Abebe Diro

Other Supervisor BITS

Prof. Kamlesh Tiwari

Other Supervisor RMIT

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
BITSRMIT024B001245
Transfer Learning for Space Systems Anomaly Detection

Project Description

This project aims to develop anomaly detection in space systems by utilizing and advancing transfer learning techniques. By adapting sophisticated algorithms developed in other domains to the unique challenges of space exploration, the study seeks to significantly improve the accuracy and speed of anomaly detection in space missions. The project expects to generate new algorithms in the area of space systems engineering and artificial intelligence, using an innovative approach that is interdisciplinary, utilizing new techniques from machine learning, data science, and aerospace engineering. The integration of transfer learning into space systems represents a pioneering effort to cross-pollinate between disciplines, enhancing the capability to predict and mitigate potential anomalies in complex space missions. his project should provide significant benefits, such as increasing the safety and reliability of space missions, reducing the cost and time associated with diagnosing and mitigating system anomalies, and fostering a deeper understanding of the operational dynamics of space systems. Moreover, by accelerating the development of adaptable, intelligent systems for anomaly detection, the project is expected to contribute to the broader goals of space exploration, including the expansion of human presence in the solar system and the enhancement of our ability to monitor and study space environments.

BITS Supervisor

Dr. Ashutosh Bhatia

RMIT Supervisor

Abebe Diro

Other Supervisor BITS

Prof. Kamlesh Tiwari

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Artificial Intelligence
Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems
Information Technology
BITSRMIT024B001342
FIELD EFFECT TRANSISTOR (FET) BASED SENSOR FOR MACHINE LEARNING ENABLED NON-ENZYMATIC MULTIPLEXED BIOMARKER/PATHOGEN DETECTION

Project Description

The project delves upon conducting non-enzymatic sensing of multiple bioanalytes, while incorporating ML techniques to autonomously acquire knowledge from data, identify patterns, and make predictions based on a substantial dataset. Herein, the fabrication of a field-effect transistor (FET)-based sensor has been proposed with an aim to enhance sensitivity. Over the past few decades, there has been a reduction in the size of the efficient FET to a few micrometers. Such size reduction alongwith improvement of catalytic properties have emerged as a significant factor motivating researchers to employe them in applications such as flexible wearable devices. ML algorithms are employed to acquire knowledge from data, detect patterns, and classify the data. Various objectives of the proposed project are: • Fabrication of flexible FET sensor: Design and optimization • Biomarkers detection: Deposition and optimization of nanomaterials or semiconductors to detect bioanalytes. • Non-Enzymatic sensing: To reduce the complexity of device fabrication for mass production, to obtain the stable and reproducible device a non-enzymatic approach will be followed. • Integration of ML: To enable the real time automated and precise prediction of biomarker. Methodology: • To determine the dimensions of dielectric layer, source, drain, gate and nanomaterials. • Obtaining the characteristics of FET in the presence of biomarkers with non-enzymatic method. • Validating the selectivity with the help of electrical characteristics of FET. • Calibration and Efficiency Optimisation by Reproducibility study for the biomarkers. • Train ML models to recognise biomarker signatures using labelled sensor data and develop a reliable technique for automated biomarker detection. • Verify the accuracy of the ML-enabled detection by testing the sensor's performance with actual biological samples and comparing the results to those obtained using accepted techniques. • Comparing the developed sensor platform to other biomarker detection methods, determine whether it is more economically viable. The overall goal is to bring about a significant transformation in the realm of biomarker detection. This will be achieved through the creation of a versatile, highly responsive platform that incorporates machine learning capabilities. The anticipated outcome of this endeavour is a platform that will have far-reaching implications for medical diagnostics and scientific research applications.

BITS Supervisor

Sayan Das

RMIT Supervisor

Dr Aaron Elbourne

Other Supervisor BITS

Sanket Goel

Other Supervisor RMIT

Professor Sumeet Walia

Required discipline background of candidate

Discipline
Electrical and Electronics Engineering, Power Engineering
Engineering, Engineering Physics
Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics
BITSRMIT024B001345
Privacy Preserving Technologies for Securing Healthcare Data

Project Description

Sharing of health data for secondary uses such as research and public policy development has many benefits, but also risks if information about an individual's health record can be inferred. Ensuring healthcare data privacy preservation technology is designed to work as per requirements is essential. The requirements for correct functioning of these techniques includes training of both researchers and the individuals. Data is now gathered and possibly used to train AI models from various sources including clinical trials, participatory health-enabling technologies and other health/medical-related records. These are in addition linked, for research, population disease surveillance, risk prediction etc. The increasing use of participatory health enabling technologies and integration of person-generated data with formal healthcare provider data, adds another layer of complexity. Thus, the design of healthcare privacy preserving techniques needs to be considered from all perspectives. The aims of this project are: Design of a process for testing of techniques used for privacy preservation of Healthcare systems. Design process for verification of functionality with ML based systems. Design and implement customized ML scenarios which providing protection with bounds on information leakage. The project will explore various mechanisms to evaluate suitability of the existing techniques and their vulnerabilities given a set of constraints.

BITS Supervisor

Prof. Shubhangi Gawali

RMIT Supervisor

Prof. Asha Rao

Other Supervisor BITS

Neena Goveas

Other Supervisor RMIT

Amy Corman

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
Mathematical Sciences
BITSRMIT024B001346
DESIGN AND DEVELOPMENT OF METAMATERIAL BASED DIELECTRIC RESONATOR ANTENNA FOR IoT APPLICATIONS

Project Description

The Internet of Things (IoT) represents the communication between physical objects (‘things’) through the use of sensors or other devices. Machine-to-machine (M2M) is communication between devices that are part of the IoT. Satellite communication technologies have a long history of use for telemetry and M2M applications. They are the only networking platform capable of providing truly universal coverage anywhere on the planet, including at sea and in remote unpopulated areas. Satellite solutions vary from low data rates to a higher bandwidth for real-time applications. For the satellite communication at GHz frequency requires a wideband, high gain circular polarized antenna. In this proposal, a metamaterial-based dielectric resonator antenna (DRA) with high gain and wide impedance bandwidth for IoT applications is proposed. In general, for wireless applications patch antennas are used due to their compact size and low cost but they suffer from low radiation efficiency due to their conductor losses. DRAs, are widely used in recent wireless applications because of their numerous advantages and attractive features like lightweight, low cost, no metallic losses, and relatively wide impedance bandwidth. DRA design helps in improving the bandwidth by reducing the quality factor. The main problem associated with a higher-frequency band is the high path loss with short-distance communication due to the short wavelengths. To overcome these issues, high-gain antennas are required to solve the problems of high path loss and increase the transmission range related to the high-frequency band. DRAs show higher radiation efficiency even at higher frequencies due to the absence of intrinsic conductor loss and surface wave loss but it offers low gain. The proposed DRA is designed along with the metamaterial structure to achieve high gain. The proposed structure can be used in the frequency band suitable for IoT. OBJECTIVES • Design and optimization of a compact Metamaterial-based Dielectric Resonator Antenna (MDRA) suitable for IoT frequency bands (2.4 GHz and 5 GHz) • Fabrication of designed antenna prototype using suitable materials. • Measurement of different parameters (return loss, gain, axial ratio, etc) of the proposed design to characterize the performance of the antenna to evaluate its suitability for IoT applications. • Comparison of simulated and measured results.

BITS Supervisor

Runa Kumari

RMIT Supervisor

Wayne Rowe

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Electrical and Electronics Engineering, Power Engineering
Engineering, Engineering Physics
Materials, Composites, Material Science, Functional Materials, Mettalurgical Engineering
PHYSICS
BITSRMIT024B001326
2. Investigating the potential of using construction and demolition wastes as a raw material for the development of sustainable binder

Project Description

Background: From its origin in the 18th century till now, ordinary Portland cement (OPC) remained one of the most widely used construction materials. Its outstanding properties like high strength and durability also provide the advantage of getting tailored as per user requirements. Such characteristics make OPC fall under materials with extensive adoption and a threat to Earth's ecosystem. Currently, the CO2 emissions of OPC are estimated to be around 8% per year, which is expected to rise due to growing infrastructural needs. As such, alternatives are required to be developed for the sustenance of sustainability along with growth. The utilization of supplementary cementitious materials (fly ash (FA), blast furnace slag (BFS), metakaolin (MK), etc.) can be one of the options, but their incorporation is somewhat limited. Furthermore, their composition varies depending on the manufacturing method adopted. Besides, industrial wastes such as stone, demolition, and other related waste streams possess enough crystallinity, restricting their usage to fillers. Thus, novel techniques must be developed to cover the existing gaps. Geopolymerization, a sub-set of alkali-activation, can be of immense use in the present scenarios due to its wide acceptability of transforming waste streams into ingenious products. It fundamentally relies on activating materials, preferably with a high amount of silicon (Si) and aluminum (Al), to obtain the desired engineering properties. The early transcripts of this technique can be traced back to the 19th century when Prudon introduced it as alkali-activation, later called geopolymerization by Prof. Joseph Davidovits in the late 1970s. High early strength, extensive resistance against fire, effluents, and climatic conditions, and low greenhouse gas emissions compared to OPCs are some of its most desirable properties. The report proposes valorizing construction and demolition wastes (CDW) through geopolymer technology. Every year, around 615 million tons [1,2] of such waste is generated, which is illegally dumped without subjecting them to prior treatments, making it a threat to flora, fauna, and humankind. However, reports from the study of Robayo-Salazar et al. [3] have shown that CDW elemental topology is rich in Si and Al-containing minerals, making it suitable for use as a precursor, viz., geopolymerization. It can also be corroborated by the x-ray fluorescence spectroscopy (XRF, Epsilon 1, Malvern Panalytical, USA) conducted o

BITS Supervisor

Dipendu Bhunia and Professor

RMIT Supervisor

Prof. Guomin (Kevin) Zhang

Other Supervisor BITS

Other Supervisor RMIT

Dr Chamila Gunasekara

Required discipline background of candidate

Discipline
Civil Engineering, Structural Engineering
Construction Eng/Management and Materials
Design, Design Engineering, Sustainable Design
BITSRMIT024B001327
1. Investigation of the Seismic Behaviour of Masonry Infill Walls with Nickel-Chrome Plating Sludge (NCPS) Bricks

Project Description

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. Research Plan : The research plan 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 BITS

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
BITSRMIT024B001339
Empowering Clinical Decision Support through Explainable ClinicalNLP

Project Description

Clinical notes obtained from various sources including electronic health records (EHRs), physician documentation, and medical literature contain valuable medical history and evidence associated with individuals. Leveraging this information can lead to more precise diagnoses, prognoses, and treatment plans. Explainable Clinical Natural Language Processing (ClinicalNLP) entails applying NLP techniques in healthcare with an emphasis on transparency and interpretability. NLP is utilized in healthcare settings to analyze and extract information from these clinical documents. However, employing neural network techniques to analyze such data may face challenges in terms of explainability. In ClinicalNLP, the concept of "explainable" emphasizes the significance of comprehending and interpreting the decisions generated by NLP models. This is especially critical in healthcare, where decisions directly influence patient care and outcomes. The goal of Explainable ClinicalNLP is to render the process and outcomes of NLP models transparent and comprehensible to healthcare professionals, patients, and other stakeholders. The objectives and proposed methodology of the project are as follows: (1) To develop a comprehensive quality control and pre-processing pipeline for clinical text: This involves creating a systematic and robust framework to ensure the accuracy, reliability, and usability of clinical text data. This pipeline will serve as a crucial step in the data preprocessing phase, where raw clinical text is transformed into a format suitable for further analysis and interpretation. (2) To Develop Contextualised, Interpretable Models: Using machine learning models that produce interpretable outputs. Further, analyzing the importance of different features or words in the NLP model's decision-making process,will provide insights into which factors influence the model's predictions. We will consider the context of clinical texts and consider domain-specific knowledge to improve the accuracy and relevance of NLP analyses. (3) To Develop Intuitive Visualization:This objective focuses on presenting the results of NLP analyses in a visually intuitive manner, to help understand the patterns and relationships in the data. Setting up interactive visualisations will reduce barriers for clinicians to directly interact with the data to make informed decisions. (4) Validation:We will closely work with healthcare professionals to set up validation pipelines.

BITS Supervisor

Satnik Mitra, Assistant Professor

RMIT Supervisor

Sonika Tyagi, Associate Professor

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing
Bioinformatics
Data Science, Data Mining, Data Security & Data Engineering
Health, Digital Health
BITSRMIT024B001340
Standardizing Medical Records into Electronic Health Records: End to end solutions for legacy systems

Project Description

Ensuring medical data is available in the correct format is essential for predicting clinical outcomes and improving patient care. Electronic health records (EHRs) have typically been adopted in institute-specific ways. This lack of standardization of EHR data poses a significant challenge, especially concerning data formatting, clinical terminology, analytical methods, and procedures. This has been handled by EHR-QC (Ramakrishnaiah et al 2023), a tool comprising two modules: the data standardization module and the preprocessing module. The data standardization module migrates source EHR data to a standard format using advanced concept mapping techniques, surpassing expert curation in benchmarking analysis. The implementation of EHR systems in developing nations is further complicated as many data parameters are gathered in legacy hardware and on non-electronic media. The lack of accessible data will prevent potential benefits of AI-based solutions from reaching patients. To address this challenge, we need an approach offering mechanisms to extract data from legacy systems and non-electronic media to solve this issue. This can then be incorporated into the data pipeline to ensure standardized EHR output. Aim of this project are: Survey of existing EHR systems in Indian healthcare settings for their accessibility and usability Design and develop data extraction mechanisms from legacy systems Design and implement customized data conversion modules [Ramakrishnaiah et al, Elsevier, Journal of Biomedical Informatics, Volume 147, November 2023,104509, , https://www.sciencedirect.com/science/article/pii/S1532046423002307?via%3Dihub ].

BITS Supervisor

Neena Goveas

RMIT Supervisor

Sonika Tyagi, Associate Professor

Other Supervisor BITS

Prof. Shubhangi Gawali

Other Supervisor RMIT

Prof. Asha Rao

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
BITSRMIT024B001331
Electrobiomethanation of organic waste for resource recovery and circular economy

Project Description

Preamble: Conventional biomethanation of organic wastes, including food waste, leads to the accumulation of volatile fatty acids due to the slow rate of methanogenesis, long retention times, and process instability. Electrobiomethanation (EBM) is a novel approach developed by the Principal Investigator, Prof. P. Sankar Ganesh, to address the shortcomings of biomethanation by facilitating faster conversion of organic matter to methane through enhanced electron transfer, enabling co-digestion of complex substrates, offering precise control of critical process parameters, and potentially improving digestate quality. However, further research is needed to optimize and scale up EBM technology. Aim: The project aims to use electrobiomethanation to treat organic waste and increase the production of methane and other value-added products. Objectives: • To enhance conventional biomethanation by incorporating electrobiomethanation, thereby increasing methane content and improving process stability and resource recovery during organic waste treatment. • To identify the optimum operational parameters of electrobiomethanation, such as applied potential, pH, electrode material, electrode geometry, and temperature for maximum methane generation. • To apply electrobiomethanation for food and other organic waste treatment as sole substrates or in combination. Methodology: Electrobiomethanation reactors (EMBR) will be designed, fabricated, and operated to treat organic waste and optimize process stability and methane production. Setting up EMBR will require environmental biotechnology, chemical engineering, and electrical and electronic engineering expertise. Our team will optimize substrate ratios, implement effective pretreatment methods, and manage operational parameters. However, selecting appropriate electrodes and fine-tuning the optimum power supply are pivotal elements that demand specialized knowledge. This interdisciplinary approach ensures a comprehensive and successful project execution by leveraging the diverse skills and insights of each discipline. Specific focus will be given to the operational parameters of EBMR, such as applied potential, pH, and electrode characteristics. These parameters will be tested at varying configurations to fix the best combination for maximizing methane production. Further, the investigation will focus on the long-term stability, economic feasibility, scalability, and environmental impact of EMBR.

BITS Supervisor

P. Sankar Ganesh and Professor

RMIT Supervisor

Nicky Eshtiaghi and Professor

Other Supervisor BITS

Dr. Ankur Bhattacharjee

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Biotechnology
Chemical Engineering
Environmental Engineering
Environmental Science and Engineering
BITSRMIT024B001333
Spacecraft thermal management through high-temperature Heat Pump System operable in microgravity

Project Description

The objective of the research project is to design and develop a high-temperature heat pump system capable of efficiently rejecting heat in satellite environment of microgravity. The use of heat pumps to improve the radiation heat dissipation from satellites is extremely important because of the ever increasing heat created by electronic systems with higher power density. Modern satellites need optimal temperatures for their delicate electrical components to work properly. Heat pumps can actively extract surplus heat and radiate it at high temperatures to keep the satellite's inside temperature within limits. Specific demands for such a system working in microgravity are: Oil free, Low maintenance, Compact, Low mass, Variable frequency etc.

BITS Supervisor

Mani Sankar Dasgupta

RMIT Supervisor

Dr. Sara Vahaji

Other Supervisor BITS

Assistant Professor Suvanjan Bhattacharyya

Other Supervisor RMIT

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
Engineering, Engineering Physics
Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics
BITSRMIT024B001330
Exploring Consumer Behaviour and Supply-chain Strategies of E Vehicle in India

Project Description

Objectives The study has four-fold objectives, touching upon the demand for and the supply of the EV market. 1. To estimate the potential market of EVs for different groups of customers in India. 2. To examine consumer behaviour by analyzing various socio-economic factors influencing the adoption rate of EVs in India. 3. To evaluate the performance of the supply-chain system of EVs and select the appropriate supply chain configuration for EVs markets. 4. To find optimal locations of EV charging stations in Rajasthan India. . Introduction The automobile sector plays a vital role in economic development by generating employment opportunities (Kang and Lee 2019). According to the Society of Indian Automobile Manufacturers (SIAM), the Indian automobile sector, which is one of the fastest-growing sectors in India, accounts for about 6 per cent of the Gross Domestic Product (hereafter GDP). More importantly, the sector contributes about 50 per cent of India's manufacturing output by providing employment opportunities to more than 35 million people. As per the data released by the SIAM, 4 million passenger vehicles were produced in India during 2018-19, and the country's automotive sector has been ranked fourth largest in the world. The overall automobile production, which includes passenger, commercial, three-wheelers, two-wheelers, and quadricycle, reported an annual growth rate of 6.25 per cent, while the automobile exports grew by 14.50 per cent during 2018-19. Not surprisingly, despite the recent upheavals in the sector, the gross turnover of the automobile manufacturers in India stood at $67 billion in 2016-17, and the industry experts forecasted that the gross turnover would reach about $250 billion by 2030. An analysis of the composition of the automobile industry reveals that the two-wheelers account for almost four-fifths of the domestic market share, followed by passenger vehicles, which consists of 13 per cent of the domestic market share. Interestingly, commercial vehicle and three-wheelers constitute the remaining part of the domestic market share. Less impressive is that ICE vehicles are widely perceived as a major contributory cause of Greenhouse gas emissions (Ajanovic 2014; Jochem et al. 2016). In economics parlance, the transport sector, particularly the automobile sector, is the major source of a negative externality. According to Singh et al. (2019), in spite of the low car density, the transport sector, which accounts for about two-

BITS Supervisor

Satyendra Kumr Sharma

RMIT Supervisor

Dr Su Nguyen

Other Supervisor BITS

Other Supervisor RMIT

Prof. Prem Chhetri

Required discipline background of candidate

Discipline
MBA (Operations / Supply Chain and Logistics)
ME (Industrial/Production Engineering)
BITSRMIT024B001337
Hybrid Wirelesss Technology for Integrated Ground-Air-Space Networks

Project Description

The project delves into developing protocols and algorithms tailored for adopting millimeter-wave (mmWave), free-space optical (FSO), and terahertz (THz) wireless technologies within integrated ground-air-space communication networks. The project is motivated by the complementary characteristics of THz and FSO for space communications while employing mmWave and RF technology in the terrestrial network. Addressing the challenges posed by dynamic scenarios within shared spectrum environments, the project prioritizes spectrum allocation, deep learning methodologies, interference mitigation, and radio channel adaptation. The project aims to autonomously optimize spectrum usage, mitigate interference, and adjust to fluctuating channel conditions in real-time by leveraging state-of-the-art techniques, notably machine learning algorithms. Objectives of the project are as follows: (a)Design and implement advanced protocols and algorithms optimized for the unique characteristics of mmwave, FSO, and THz wireless technologies, ensuring efficient integration and operation within integrated ground-air-space communication networks. (b) Develop solutions to address the dynamic challenges encountered in shared spectrum environments, focusing on spectrum allocation strategies, deep learning methodologies for interference prediction and mitigation, and adaptive radio channel adaptation techniques to maintain robust communication links. (c) Implement intelligent algorithms capable of autonomously optimizing spectrum utilization, dynamically adjusting transmission parameters, and mitigating interference sources in real-time, leveraging machine learning approaches to continuously adapt to changing environmental conditions and network dynamics. (d) Explore innovative methodologies and technologies to catalyze a paradigm shift in wireless networking, introducing novel approaches to spectrum management, interference mitigation, and dynamic resource allocation, with significant implications for critical applications, including disaster response, surveillance, and remote sensing. The project methodology involves rigorous simulations, mathematical modeling and analysis, and verification of developed algorithms through real-time empirical data. Through meticulous research, development, and deployment endeavors, the project endeavors to redefine the capabilities of integrated ground-air-space networks, paving the way for a more robust and efficient communication network.

BITS Supervisor

Syed Mohammad Zafaruddin, Associate Professor

RMIT Supervisor

Akram Hourani, Associate Professor

Other Supervisor BITS

Other Supervisor RMIT

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
Information Technology
Networks and Communications, Wireless Comms, Telecommunications
BITSRMIT100039
Machine learning based prediction of mechanical behaviour of additively manufactured parts for known type, scale and distribution of defects

Project Description

Additive manufacturing (AM) process introduces unique defects in the parts, such as the lack of fusion defect and delamination between the layers in metallurgically dissimilar AM parts, making them inferior in fatigue and fracture resistance, which are critical for Aerospace structures. The precise mechanical behaviour of additively manufactured parts for known defect types and loading conditions is unknown. A trained deep learning network, such as vision deployed Pulse-Coded Neural Networks (PCNN), on the effect of defects on mechanical behaviour can benefit the structural health monitoring of bespoke AM structures in aerospace applications. The present research aims to develop numerical models to predict the effect of known defects on mechanical behaviour, taking into account microstructural and macrostructural characteristics. The findings will be mapped to the laser power and rasterization parameters of the AM method itself. Validate the numerical models using a limited number of experiments, generate sufficiently large data using the validated numerical models and train machine learning (ML) models. Finally, we will test the ML models on known AM process-defect-mechanical performance mapping. The methodology involves AM of tensile and flexural specimens with known defects and conducting tensile and 3-point bending tests. Use suitable sensors and computational algorithms to determine fracture initiation and propagation and relate them to defects and overall strength.

BITS Supervisor

Prof. Srinivasa Prakash Regalla Dean (Institute-wide), Practice School Division, BITS Pilani

RMIT Supervisor

Sabu John, Professor

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing
Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics
BITSRMIT100043
Faster Threat Detection and Malware Analysis in Network Dataplane.

Project Description

Objectives of the Proposed Research: The proposed research aim: 1. To design and implement a distributed model for DDoS attack detection at the dataplane level 2. To design and implement a distributed processing model for executing ML models for malware analysis in the dataplane 3. To design a secure protocol for exchanging state information among the switches within the dataplane 3. Research Gaps The current security models majorly work on analyzing the packets in the control plane which is more time consuming and affects the network majorly by the time the attack is recognized. The packets incoming into the traffic could be malicious or non-malicious. The proposed security model helps in identifying any kind of malicious payload attached and therefore drops the malicious traffic from the data plane itself. There are already some works in the literature which are using dataplane for threat detection but they don’t address the following questions: 1. Can the model detect DDOS attack in the data plane itself before it reaches the control plane? 2. Can the switches communicate among themselves with the information in the network so as to reach some decision regarding any attack or malicious traffic? 3. Implementing Machine Learning models on the data plane over the switches in a logic split manner to detect the attacks? Are we able to distribute the processing of the ML models on the data plane? 4. Is the time reduced to detect the malicious traffic in the data plane? 5. Are we able to filter out most of the false positives in the data plane itself before the data packets hit the control plane?

BITS Supervisor

Dr Hari Babu Kotakula

RMIT Supervisor

Prof. Iqbal Gondal, Associate Dean, Cloud, Systems & Security

Other Supervisor BITS

Other Supervisor RMIT

Associate Professor Mark Gregory

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
BITSRMIT100047
Medical Diagnosis based on Fusion of Small Multimodal Data

Project Description

Aim: To design a neural network system for an automatic diagnosis based on limited diagnostic data from different modality sensors. Methodology: We will design an algorithm that makes the medical diagnosis based on the combined information from multiple sources, such as different modality sensors or imaging methods. The data can have either single or multiple labels, such as, for example, the type of the disease and the stage of the disease. Current trends are to build very complex single-network multimodal and multi-label structures. The data, training time, and hardware requirements are incredibly high. We propose to replace it with a modular system of interconnected classifiers, each working on a different sub-task. The modules will have simple structures and relatively low data and training requirements. The final decision will be based on the type of connections and information flow between these modules. Each module can be easily re-trained; modules can be switched on or off depending on the application requirements.

BITS Supervisor

Abhijit Das, Dr

RMIT Supervisor

Margaret Lech, Professor

Other Supervisor BITS

Aritra Mukherjee

Other Supervisor RMIT

Richardt Wilkinson, Dr

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
Neural Networks
Robotics, Sensors, Signal Processing, Control Engineering
BITSRMIT024B001276
Optimizing Systems for Edge-Based Machine Learning Models

Project Description

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 BITS

Other Supervisor RMIT

Dr Araz Nasirian

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
BITSRMIT024B001278
Unravelling the effects of tool and workpiece interactions on functional surface generation in mechanical micromachining

Project Description

The recent technological shifts have led to a tremendous rise in the miniaturised devices, components, features and functional surfaces which find their applications in space, optics, electronics, defence, medical and automotive industries. The surface functions, including its physical and chemical behaviour, can be controlled by creating microstructures on the surface and, therefore, are in huge demand. Various micro-manufacturing techniques, including electric discharge machining, laser-based micromachining, Lithography, electroplating and moulding (LIGA), deep reactive ion etching, deep UV lithography or mechanical micromachining are popular methods for generating the micron-sized features on the substrate materials or producing the functional surfaces. Mechanical micromachining offers high precision, flexibility in the choice of work-piece materials and increased efficiency attributable to very low cycle time and ease of material removal. 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 models and tool wear models are 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. Aims and Methodology: The research project aims to gain insights into the process, model validation, and optimise the micro-machining process. There is a great need to examine the effect of these parameters on cutting forces, tool wear, surface roughness, and damage. This research project aims to investigate the mechanical micromachining process through theoretical and exper

BITS Supervisor

ANUJ SHARMA

RMIT Supervisor

Songlin Ding, Professor

Other Supervisor BITS

Other Supervisor RMIT

Required discipline background of candidate

Discipline
Additive Manufacturing, Manufacturing, Automation
ME (Industrial/Production Engineering)
Mechanical Engineering
Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics
BITSRMIT024B001336
Model based Design for ML based Devices for Healthcare

Project Description

Ensuring healthcare devices are designed to work as per requirements is essential. The requirements for correct functioning include latency bounds, measurement and analysis within constraints, data storage etc. The design of healthcare systems using Machine Learning (ML) based models is now gaining momentum. These ML models can be part of autonomously functioning devices. Even though functionality offered by ML models is desired, it is typically used as a black box. This makes it difficult to incorporate it in healthcare related applications as testing and verification of its functioning is time consuming. The aims of this project are: 1) Design process for testing of ML models within the constraints of Healthcare systems. 2) Design process for verification of functionality within constraints for ML based systems. 3) Design and implement customized ML model testing. Model based development of systems using ML. The project will explore various mechanisms to evaluate suitability of a given ML model given a set of constraints.

BITS Supervisor

Neena Goveas

RMIT Supervisor

Prof. Asha Rao

Other Supervisor BITS

Other Supervisor RMIT

James Baglin

Required discipline background of candidate

Discipline
Computer Science and Engineering/Computer Engineering
Computer Science and Information Systems
Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems
Data Science, Data Mining, Data Security & Data Engineering
Mathematical Sciences
BITSRMIT100048
Structure-Function Relationship of a Flippase-conjugated Guanylate Cyclase in Toxoplasma gondii

Project Description

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 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

Paul Ramsland, Professor

Other Supervisor BITS

Ratnesh Kumar Srivastav, Dr.

Other Supervisor RMIT

Christian Doerig, Professor

Required discipline background of candidate

Discipline
Biology, Cell Biology, Niological Sciences
Biotechnology
Health, Digital Health
BITSRMIT100051
Iron nanoparticles impregnated composite electrospun nanofibers for arsenic and microbes filtration from groundwater stream

Project Description

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

Prof. Namita Roy Chowdhury

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
BITSRMIT100059
Optimisation of Renewable Energy Sources (RES) and Energy Storage Systems (ESS) in a Microgrid