Research projects in Information Technology

Technologies emerge from a society’s cultural imagination, sparking new ways to imagine the future. Today, Artificial Intelligence (AI) – as the technical capability of a system ‘to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation’ [1] – is formed into virtually any digital system that we draw upon to interact with each other and the world around us.

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.

Agent-based computational simulations are now widely employed to study the evolution of behaviour, e.g., predator-prey simulations, the evolution of cooperation and altruism, the evolution of niches and food chains. These methods implement evolutionary processes in virtual populations of software agents and explore the evolution of their behaviour in diverse environments. Many behaviours that are not well understood in biological systems, that are difficult or impossible to measure in real environments, can be accurately captured and understood using these techniques.

"A picture is worth a thousands words"... or so the saying goes. How much information can we extract from an image of an insect on a flower? What species is the insect? What species is the flower? Where was the photograph taken? And at what time of the year? What time of the day? What was the weather like on the day the photograph was taken? This project aims to extract useful ecological and/or horticultural data from digital images by analysing their content.

In this project we are interested in exploring new paradigms for solving Combinatorial Optimisation problems, and generally NP-hard ones. One direction of research could consist in using approximation algorithms for deriving dual bound within a branch-and-bound algorithms. Other directions could use Machine Learning or new decompositions. This subject is generally quite open so it is important to be highly creative.

The brain is a complex machine and brain function remains yet to be fully understood. This project works at the intersection of dynamical modelling, statistical signal processing, statistical inference and machine learning to develop subject specific mathematical models of the brain that can be used to infer brain states and monitor and image the brain.

Life is exciting and challenging at the same time. Some people have it easy and some have it hard but we all need advice that can help us to live rich, fulfilling lives. By drawing on psychological, sociological, economic and web data this project will apply machine learning to build a recommendation engine that can provide life advice and predictions to individuals based on their current life situation and past experiences. The goal is to help people find ways to improve the quality of their lives through incremental adjustments suggested by the recommendation engine.

This project aims to develop resource management techniques including scheduling and scaling algorithms for container-based virtual clusters in cloud data centres powered with renewable energy sources. Algorithms are designed to optimise renewable energy use while meeting the Quality of Service requirements of applications running on the cluster. Specifically, the project aims to:

1. Define an architectural framework and principles for renewable energy-aware management of containers in cloud data centres;