Research projects in Information Technology

Displaying 11 - 20 of 186 projects.

Detecting Threats in Temporal Networks

A PhD is available for an Australian citizen with our industry partner The AiLECS Lab. The project is Detecting Threats in Temporal Networks. The project aims to better understand communications in networks of criminal activity.

This will be led by OPTIMA AI Dr John Betts and OPTIMA CI Prof. Peter Stuckey at Monash University, and Dr Janis Dalins and Dr Campbell Wilson at The AiLECS Lab.

Brief description of the project:

Supervisor: John Betts
A futuristic image of outlines of a group of 14 people as if seen through a scanner.

Platforming participatory research data governance

Research data governance is an under-explored issue, and technical infrastructures to support the transparency and control of data collected in human research studies (from medicine to social sciences) focus primarily on the researchers rather than the people whose data has been collected. While data protection legislation worldwide is increasingly regulating what companies can do with their customers' data and providing legal mechanisms for customers to access and control such data, the same cannot be said for data collected in research studies.

Supervisor: Prof Patrick Olivier

AI-augmented coaching, reporting and its assessment

This project will develop general cutting edge generative AI and natural language processing methods to advance AI-augmented human-in-the-loop coaching and associated training planning and outcome reporting.

Supervisor: Dr Levin Kuhlmann

Brain network mechanisms underlying anaesthetic-induced loss of consciousness

This project focuses on brain network mechanisms underlying anaesthetic-induced loss of consciousness through the application of simultaneous EEG/MEG and neural inference and network analysis methods. In this work we study the effects putative NMDA antagonists xenon, a potent anaesthetic, and nitrous oxide, a weak anaesthetic, on anesthetic-induced changes in brain mechanisms and networks.
Supervisor: Dr Levin Kuhlmann

Model-based depth of anaesthesia monitoring

This project involves model-based depth of anaesthesia monitoring using autoregressive moving average modelling and neural mass and neural field modelling of the electroencephalographic (EEG) signal. This will be achieved through frequency domain and time domain state and parameter estimation techniques to infer model states and parameters in real time to simultaneously track the anaesthetic brain states while inferring underlying physiological changes.
Supervisor: Dr Levin Kuhlmann

Epileptic Seizure Prediction

Seizure prediction algorithms will be developed using the one-of-a-kind ultra-long-term human intracranial EEG dataset obtained from the Neurovista Corporation clinical trial of their Seizure Advisory System, or data from other implantable or wearable devices. This involves consideration of both feature-based machine learning or data science approaches and neural mass parameter estimation approaches to classify the EEG and predict seizures. Recent approaches focus on critical slowing as a marker for seizure susceptability and the influence of brain rhythms.

Supervisor: Dr Levin Kuhlmann

Securing Generative AI for Digital Trust

Project description: Generative AI models work by training large networks over vast quantities of unstructured data, which may then be specialised as-needed via fine-tuning or prompt engineering. In this project we will explore all aspects of this process with a focus on increasing trust in the model outputs by reducing or eliminating the incidence of bugs and errors.
Supervisor: Xingliang Yuan
Visualisation of the neuro-symbolic learning and planning framework presented in [1] where red circles represent action variables, blue circles represent state variables, grey circles represent the activation units and w's represent the weights of the neural network.

Safe Neuro-symbolic Automated Decision Making with Mathematical Optimisation

Planning is the reasoning side of acting in Artificial Intelligence. Planning automates the selection and the organisation of actions to reach desired states of the world as best as possible. For many real-world planning problems however, it is difficult to obtain a transition model that governs state evolution with complex dynamics.

Supervisor: Dr Buser Say
Visualisation of a plan generated by SCIPPlan for an example navigation domain.

Safe Continuous-time Automated Decision Making with Mathematical Optimisation

SCIPPlan is a mathematical optimisation based automated planner for domains with i) mixed (i.e., real and/or discrete valued) state and action spaces, ii) nonlinear state transitions that are functions of time, and iii) general reward functions. SCIPPlan iteratively i) finds violated constraints (i.e., zero-crossings) by simulating the state transitions, and ii) adds the violated constraints back to its underlying optimization model, until a valid plan is found.

Supervisor: Dr Buser Say
A linear relaxation of an integer programming problem

End-to-End Prediction and Optimisation for Neuro-Symbolic Artificial Intelligence

Optimisation methods, such as mixed integer linear programming, have been very successful at decision-making for more than 50 years. Optimisation algorithms support basically every industry behind the scenes and the simplex algorithm is one of the top 10 most influential algorithms. Major success stories include rostering nurses in hospitals, managing chains of organ transplants, planning production levels for manufacturing, routing delivery trucks for transport, scheduling power stations and electricity grids, to name just a few.

Supervisor: Dr Edward Lam