Honours and Masters project

The aim of this project is to understand the computations underlying animals’ choice in dynamic and changing environments. The natural environment is multisensory, dynamic and changing, requiring animals to continually adapt and update their learned knowledge of statistical regularities in the environment that signal the presence of primary needs like water, food and mates. Yet, how the brain adapts and updates itself to the non-stationary and dynamic attributes of natural environments remains unexplored.

The tennis tour is a series of tennis tournaments played globally over a calendar year, where professional tennis players compete for prize money and ranking points. The structure of the tennis tour is organised into different tiers for both men and women, including grand slam tournaments and ATP/WTA tour events. In this project we use stochastic processes to model and simulate the tour under different experimental rules.

This project seeks to explore and trial new map morphing representations for seeing river water quality data sets more effectively over time and space. 

We are particularly focusing on the Melbourne and the region of Victoria, but expect the visualisation to be applicable to any geographical region.  

This research aims to bridge a critical accessibility gap in digital navigation tools by developing an inclusive, intelligent system that combines map services, street-level imagery, and large language models (LLMs). Current systems often fail to support marginalised users—such as older adults, people with vision impairments, or those with limited mobility—by overlooking nuanced environmental cues such as footpath obstructions, ramp availability, or visibility of building entrances. By democratising navigation, the project addresses both a technological and equity gap in urban mobility.

The research project aims to investigate:

- Multi-Model Fusion with Deep Neural Networks for Future Energy Systems (Smart Grid). 

Future energy systems are envisioned to be running decentrally with full automatic control, high proportion of renewable energy (e.g., wind & solar), and abundant storage facilities. With many types of renewable energy sources are weather and climate dependent, accurate and timely prediction on reliability risks (e.g., loss of generation, voltage issues, and thermal limit violations) due to weather/climate are often necessary.

Visually discriminating the identity of multiple (similar looking) objects in a scene and creating individual tracks of their movements over time, namely multi-object tracking (MOT), is one of the basic yet most crucial vision tasks, imperative to tackle many real-world problems in surveillance, robotics/autonomous driving, health and biology.

Chatbots for mental health are shown to be helpful for preventing mental health issues and improving the wellbeing of individuals, and to ease the burden on health, community and school systems.  However, the current chatbots in this area cannot interact naturally with humans and the types of interactions are limited to short text, predefined buttons etc. In contrast, psychologists in real-world interact with patients with multiple modalities, including accustic and visual information. Non-textual information is also essential for health observation and treatments of patients.

Autoregressive moving average (ARMA) models remain a competitive tool for forecasting low signal-to-noise ratio time series, due to their flexibility, low complexity and physical plausibility. They predict the next observation in a time series as a linear combination of a number of previous observations as well as a number of hidden (latent) random innovations. The AutoARIMA package remains a staple benchmarking tool against which forecasting techniques must be compared.

In NeuroDistSys (NDS): Optimized Distributed Training and Inference on Large-Scale Distributed Systems, we aim to design and implement cutting-edge techniques to optimize the training and inference of Machine Learning (ML) models across large-scale distributed systems. Leveraging advanced AI and distributed computing strategies, this project focuses on deploying ML models on real-world distributed infrastructures, improving system performance, scalability, and efficiency by optimizing resource usage (e.g., GPUs, CPUs, energy consumption).

Chemical exchange saturation transfer (CEST) MRI provides images of molecular information and has recently been used for the detection of malignant brain tumors and the assessment of muscle tissue in cardiac infarction. Additionally, CEST has also been used to assess changes in a neurotransmitter -glutamate (Glu)- in both brain and spinal cord and has shown potential in a number of diseases including Alzheimer’s-like dementia, Parkinsonism and Huntington’s Disease and Motor neuron diseases.