Research projects in Information Technology

Effective allocation of tasks is essential for any socially living group. This project investigates self-organised task allocation, ie groups in which tasks are not centrally assigned to individuals. In self-organised groups, individuals rather select their tasks autonomously based on their own choices and preferences. Under which conditions does this achieve the desired group outcomes?

We have a range of potential research projects on offer in partnership with VIFM - https://www.vifm.org/ - looking at ML techniques in predicting forensic diagnoses  / image analysis, across multiple data types found at VIFM. These include atomic data, text data and text documents, medical images, clinical photographs and digital pathology slides. 

This research has high potential to support our IT for social good agenda in addition to its technical attractiveness. 

Reasoning, constraint solving and optimisation technologies have made remarkable progress over the last two decades. A number of formalisms like Boolean satisfiability (SAT), satisfiability modulo theories (SMT) and their optimisation extensions (MaxSAT and MaxSMT) as well as constraint programming and optimisation (CP) and mixed-integer linear programming (MILP) can be seen as success stories in computer science.

The world is dynamic, in constant flux. However, machine learning typically learns static models from historical data. As the world changes, these models decline in performance, sometimes catastrophically so. This PhD will develop technologies for addressing this serious problem, building upon our groundbreaking research into the problem.

The world is dynamic and in a constant state of flux, yet most machine learning models learn static models from a dataset that represents a single snapshot in time. My group's research is revolutionising the field of temporal analytics. We have refocused the field on methods that are both effective and feasible for non-trivial problems.

This project works with leading researchers in the Faculty of Pharmacy to develop new artificial intelligence technologies to aide discovery of drugs to treat pharmacoresistant epilepsy.

This project concerns the investigation of suitable socio-technical data infrastructure for law-enforcement research and development. International collaboration between law-enforcement agencies, research institutions, and commercial organisations is vital to address the large scale technical challenges inherent in combating criminal network activity.  A significant issue in this work concerns the data infrastructure necessary for collaborative research into, and development of, analytical techniques and algorithmic models.

In this project, we will use machine learning methods to diagnose the health status of bee colonies and individual bees.

Bee populations are threatened worldwide due to a number of factors, including parasites and virus infections, climate change, intensive farming, and other environmental stress factors. Australia, until recently, has been relatively protected from infections, but these are now increasingly taking place here as well. 

Networked digital diagnostic, monitoring and patient treatment tools permeate medical practice. A plethora of telemedicine, national and other eHealth records, injury assessment, patient-specific devices, hospital theatre equipment tools have resulted in a multi-billion dollar industry worldwide.  Research suggests the application of these tools  to healthcare can improve clinical workflows and patient care outcomes.

Computational simulations are now widely employed to study the behaviour of social systems, examples being market behaviours, and social media population behaviours. These methods rely heavily on game theoretical modelling, usually employing populations of software agents to emulate the behaviour of human populations. Researchers construct models, usually based on known games, and empirical data, and use these to explore how the population reacts to changes. Many behaviours that are not well understood in social systems can be accurately captured and understood using these techniques.