The convergence of Artificial Intelligence (AI) with immersive technologies such as Augmented Reality (AR) and Virtual Reality (VR) is rapidly transforming the landscape of healthcare and medical training. While AI enhances decision-making through data-driven insights, AR and VR offer intuitive, spatial, and interactive environments that support diagnostics, education, therapy, and surgical planning. However, the integration of these technologies remains fragmented, with varying degrees of adoption, technical maturity, and clinical impact.
Honours and Masters project
Displaying 211 - 220 of 243 honours projects.
Context-Aware Fusion of AR, Vision Models, and LLMs for Safety Inspection
This project builds upon an existing safety inspection system framework, integrating augmented reality (AR), artificial intelligence (AI), and automated reporting. You will follow the framework to design, implement, and evaluate a fully functioning prototype system that supports safety inspections in real-world construction environments.
HandovAR: A Framework of Collaborative ICU Nurse Handover System via Augmented Reality
This project develops a collaborative handover system using an augmented reality (AR) headset display to improve ICU nurse communication. It integrates in-situ AR visualisations and a cross-reality collaboration model to address cognitive challenges and data fragmentation in handovers. The prototype aims to enhance the accuracy and efficiency of handover for practical application in high-pressure settings.
UrbanTwin-EV: YOLO-Powered Digital Twin for Electric Vehicle Traffic
This project focuses on implementing an AI-powered digital twin for intelligent electric vehicle (EV) traffic management in smart cities, utilising the YOLO algorithm. It develops a basic digital twin system designed to monitor and manage EV traffic in urban areas. The system detects and tracks EVs using feeds from traffic cameras. The digital twin simulates traffic flow, providing a visualisation of EV movement, congestion points, and route patterns.
Inclusive Intelligence: Designing a Generative AI Tool to Support Equitable Team Practices in Engineering Projects
This is a research and development project focused on designing a Generative AI tool that supports equitable team practices in software development. The project combines qualitative research, such as persona profile creation, with AI prototyping to explore how GenAI can foster inclusion, improve team dynamics, and accommodate diverse working styles in technical environments. The outcome includes both a functional AI prototype and practical resources for inclusive collaboration.
GridData-Twin: A Distributed Digital Twin Framework for Smart Grid Data Monitoring and Analytics
This project aims to develop a modular and distributed digital twin framework focused on simulating, monitoring, and analysing smart grid data. The framework will represent virtual models of grid components (e.g., loads, meters, nodes) and synchronise them with real-time or simulated data streams using distributed systems principles.
The testbed will support:
HealthPulse: Real-Time Monitoring and Anomaly Detection Using IoMT Data
This project involves building a system that processes IoMT data(such as heart rate, blood pressure, or glucose levels) from wearable devices to monitor patient health in real time.
The system uses machine learning to detect anomalies and alert healthcare providers or caregivers. It includes data preprocessing, model training, and a simple dashboard for visualization.
Probabilistic modelling using pretrained foundation models
Pretrained models
The hidden layers of pretrained foundation models, such as ChatGPT, contain useful and abstract summaries of data. From an information-theoretic perspective, they might compress the data. From a machine learning perspective, they compute useful features of the data. From a statistics perspective, they might be sufficient statistics for a parameter of interest.
Probabilistic models
Sampling from subtractive mixture models (Honours and Masters project)
What is a mixture model?
You may have learned about mixture models in a machine learning or statistics course. A mixture model with K component densities is defined by
a set of K nonnegative mixture weights summing to one, and a corresponding set of K nonnegative component densities, each of which integrates to one.The sum of the product of the mixture weights and component densities is guaranteed to be nonnegative and integrates to one, meaning it is a valid probability density.
Understanding Transgender Gender Euphoria in Play
Gender euphoria addresses times when one's lived experience aligns with their gender identity. This may be personal experiences of one's body, how one is treated by others, or through in-game experiences. Our prior research has developed an understanding of how gender euphoria comes through in video games from first-person research. This project will work toward developing and deploying a questionnaire to study this phenomenon in the wild and analyse the results.