Research projects in Information Technology

The project involves building a high-fidelity digital twin of complex urban or environmental systems by integrating GIS data, IoT sensor measurements, and domain-specific information. AI models will be developed to predict dynamic behaviors and key risk zones, and these models will be embedded into the digital twin to enable real-time simulation and visualization. The system’s performance will be evaluated in terms of prediction accuracy, computational efficiency, and usability to ensure it provides actionable insights for decision-making and planning.

The project involves building and curating a comprehensive food image dataset suitable for mobile AI applications. High-accuracy deep learning models will be trained on this dataset and then compressed into lightweight student models using knowledge distillation, enabling efficient real-time inference on mobile devices. The distilled models will be deployed and optimized on mobile platforms, with their performance evaluated in terms of classification accuracy, computational speed, and overall usability.

This project examines how films produced in Asian markets perform in terms of commercial success and critical recognition using real-world industry data. Students will compile a dataset of films from regions such as Hong Kong, China, South Korea, and Southeast Asia, drawing on publicly available sources to analyse indicators such as production budget, box office revenue, streaming platform release, and awards. Using quantitative data analysis methods, the project aims to identify patterns and factors associated with successful film outcomes.

Understanding protein structures is fundamental in food science, but traditional 2D representations often fail to convey their complex 3D shapes and interactions. This project aims to develop VR/AR applications that allow users to explore protein structures interactively and immersively, enhancing comprehension of protein function, behavior, and their roles in food systems.

This project explores the development of digital tools that measure the carbon footprint and nutritional impact of meals to support sustainable eating. It aims to integrate environmental and nutritional data into a user-friendly platform, enabling consumers, restaurants, and policymakers to make informed food choices and reduce diet-related emissions.

Goal Recognition is the task of inferring the goal of an agent from their action logs. Goal Recognition assumes these logs are collected by an independent process that is not controlled by the observer. Active Goal Recognition extends Goal Recognition by also assigning the data collection task to the observer. This Ph.D. project will provide a unified probabilistic and decision-theoretic perspective to fundamentally solve the central question: how should an observer act in an environment to actively uncover the goal of the agent?

We have several PhD  opportunities available in areas such as Multimodal Large Language Models (MLLM) for human understanding, MLLM safety, and Generative AI.

If you have published in top-tier conferences (e.g., CVPR, ICCV, ECCV, NeurIPS, etc.), you will have a strong chance of receiving a full PhD scholarship.

Exciting opportunities to work on a new Discovery Project: Enhancing learner feedback literacy using AI-powered feedback analytics!

Project description:

Security Operations Centres (SOCs) play a central role in organisational defence and are responsible for continuous monitoring, detecting, investigating and responding to cyber attacks. Organisations increasingly depend on security tools to flag suspicious activity. These tools generate alerts that analysts must examine to determine whether they represent real attacks or false positives. However, the volume of alerts continues to grow at a pace that far exceeds what human analysts can realistically review.

Two PhD scholarships are available, funded through a DECRA, which explore the use of deep learning models for uncertainty quantification.