Honours and Masters project

As games have increased in complexity, so have the worlds in which players find themselves. The automap has become a staple feature of many video games; in some, the players is allowed to edit the map itself during play (e.g., to mark important locations or lay out a course). We know about what games offer players in terms of game maps, but not how players *actually use* those features. This project will collect data on players' cartography activities in games. 

Using artificial intelligence software and unique algorithms for predictive analytics that incorporate modelling, machine learning, and data mining, we analyse, model, and build an individual’s baseline health profile against thousands (eventually millions) of similar people and their data points, along with decades of evidence-based medical and population research. Our previous work focused on the prediction of Diabetes Type Two – a major debilitating chronic disease, and a significant contributor to global deaths.

Manual medical report writing is time-consuming and subject to variability. Recent advances in large language models (LLMs) create new opportunities for automating this process. This project explores using LLMs to generate medical reports from a very large dataset, aiming to streamline workflows and support clinical decision-making. Students will work on data preprocessing, model fine-tuning, and performance evaluation, contributing to advances in medical AI.

Australia’s cybersecurity infrastructure, particularly in IoT networks, must be strengthened to meet evolving standards set by international bodies like NIST and the NSA. This project will support Australian organizations in adapting to quantum-safe standards, ensuring the protection of sensitive data and critical system

Leveraging the FLoRA adaptive learning platform, we will conduct a five-phase research program combining experimental studies and advanced trace data analysis. Through time-stamped interaction data, we aim to detect behavioural signals of metacognitive disengagement using machine learning and time-series modeling techniques. These insights will inform the development of adaptive scaffolding tools that encourage students to monitor, evaluate, and adjust their learning strategies when using GenAI.

Introductory programming remains a significant challenge for many students. A large factor impacting success is each student's motivation to engage with assessment and practice exercises. One strategy for improving student engagement is to offer multiple assessment options.

Access to education is an important issue. A major factor preventing access can be the cost of textbooks, which is a significant barrier for some students. Open Education Resources (OERs) are a popular option for reducing this financial burden, as they are free to any person with an internet connection. 

Since the COVID-19 pandemic there has been an increasing shift within higher education away from traditional lectures and towards asynchronous content delivery through pre-recorded videos. This has a number of benefits: students can consume content at their own pace, videos can be reused, and production value can be increased. However, academics typically have no training or experience in video production, so pre-recorded videos are most often just a simulacrum of a standard lecture (i.e., a slideshow with voiceover).

In human-AI collaboration, it is essential for AI systems to understand and anticipate human behavior in order to coordinate effectively. Conversely, humans also form inferences about the agent’s beliefs and goals to facilitate smoother collaboration. As a result, AI agents should adapt their behavior to align with human reasoning patterns, making their actions more interpretable and predictable. This principle forms the foundation of transparent planning (MacNally et al, 2018).

Urbanisation and climate change are accelerating environmental degradation, making cities critical battlegrounds for sustainability.