Research projects in Information Technology

Over the past decades, we have witnessed the emergence and rapid development of deep learning. DL has been successfully deployed in many real-life applications, including face recognition, automatic speech recognition, and autonomous driving, etc. However, due to the intrinsic vulnerability and the lack of rigorous verification, DL systems suffer from quality and security issues, such as the Alexa/Siri manipulation and the autonomous car accidents. Developing secure and trustworthy DL systems is challenging, especially given the limited time budget.

This project aims to define the human-centric features of mobile applications (apps) reflecting end-user human values and to model mobile app defects violating those values. The PhD candidate will compile a corpus of existing mobile apps and develop an automated “app feature values miner” to incrementally develop a new taxonomy and characterisation of human values associated with mobile app features that are to be validated with end-users and software engineers. In the next step, the PhD candidate will define a set of human values-based “anti-patterns” for mobile app features, i.e.

This PhD project is funded by a DHCRC project "Actionable data for clinicians and external accreditors in support of quality care provision and continuous accreditation". The successful applicant will work as part of a larger research team on this project which includes multiple industry partners.

Machine learning is being used to make important decisions affecting people's lives, such as filter loan applicants, deploy police officers, and inform bail and parole decisions, among other things. Machine learning has been found to introduce and perpetuate discriminatory practices by unintentionally encoding existing human biases and introducing new ones. In this project, we will develop automated testing approaches that can be used to verify that machine learning models are not biased. 

Modern map-based systems and location-based services rely heavily on the ability to efficiently provide navigation services and the capability to search points of interests (POIs) based on their location or textual information. The aim of this project is to build a next-generation navigation system by addressing limitations in the current systems – such as allowing more meaningful distance measures, modeling uncertainty in data sources and queries, and exploiting rich information from several data sources.

On their own, traffic accidents cause 1.3 million fatalities every year – and improper situational awareness is often a major cause. This project aims to exploit big spatio-temporal data to design intelligent techniques for scheduling and offloading tasks to the cloud and peer vehicles. This will ultimately meet the Quality of Service (QoS) requirements of time-critical road safety applications and increase situational awareness by automatically identifying unsafe road conditions and risky driving behaviors – and sending alerts in real time to affected vehicles.

This project aims to harness big data from ubiquitous smartphone sensors to reduce the impact of road transport on the environment. Specifically, we’ll design novel data modelling and indexing techniques to exploit the data and create a next-generation, eco-friendly navigation system which will significantly reduce greenhouse gas emissions and result in fuel saving. The initiative also aims to study the citywide impact of adapting to eco-friendly navigation on traffic, environment and road safety – therefore supporting urban planning and decision-making.

This project heavily focuses on maps (e.g. GoogleMaps or Open Street Map). We will explore various properties of road networks, including the granularity of road networks, routes and trajectories on road networks, and query processing on road networks. 

A number of inter-disciplinary collaboration exists, including transportation to hospitals, urban sprawl analysis, and geospatial in sustainability (e.g. analysing placement of rubbish bins on streets).

This project investigates 3Vs of Big Data (e.g Volume, Variety, and Velocity). 

Volume: Due to the exponential increase in data volume, it is necessary to adopt parallelism techniques to achieve reasonable query response time. The main focus will be on parallel query processing, which is the main driver for Big Data processing

This project is technical in nature and would suit a candidate with a background and interest in web programming, health informatics or health data (or a combination thereof).

One potential area of exploration for the candidate is extending the work on Pathling (developed by the CSIRO).

Another area demanding further investigation and research is that of dynamic and extensible clinical decision support through CDS Hooks.

#digitalhealth #health #FHIR #interoperability #software #EMR #CDS