Dr Guido Zuccon
This project aims to help people make better health decisions from search engines by improving the information that search queries return. Google is utilised by 80 per cent of Australians to search health symptoms, despite evidence showing that many often find incorrect and unreliable health information.
Expected outcomes include new models and methods for evaluating high-stakes search and new search technologies to help people find and recognise high quality information to make better health decisions.
Next-generation sequencing technologies have brought a revolution in biology and healthcare, while taxing the ability of scientists and clinicians to identify and process relevant data, to make sense of it all and communicate it to others in a concise and meaningful way.
This project aims to tackle this problem through fundamentally new approaches to data selection and visualisation at very large scale, actively encoding for insight into underlying biological and biomedical processes, bringing sustainable discovery of new relationships and variations within the data.
The project aims to support new approaches to medical diagnosis and treatment, and offer crucial lessons to address the broader challenge of understanding large, complex data sets.
This project investigates the challenging problem of securing real-time control of large-scale power systems.
Both industrial control systems and electricity power systems are a critical part of national infrastructures of industrial countries like Australia and Germany. The power systems are operated under real-time monitoring and control for system stability and efficiency, while the real-time control of power systems rely on 'domain separation' for the security and integrity of measurement and control data and data transmissions. Any 'air gaps' between the domains can be easily breached for a cyber attack, causing serious security threats worldwide in critical infrastructure systems including power networks.
The current practice is to monitor the integrity of the security domains through manual audits. However, manual checks are far slow to react to cyber attacks. System inspectors and maintainers may also cause unexpected and insecure incidents by accident.
The dramatic rise in massive text data has led to an increasing number of challenges in scalability and noisy information. Supervised classification has become expensive and time consuming as acquiring training sets for a large number of categories becomes more complex and classifiers are sensitive to data. Un-supervised classification has become an attractive alternative given it does not require training sets. However, un-supervised classification is still complex and there is a gap between understanding of concepts and features.
This project aims to exploit domain ontology to find specific ontology which can bridge the gap, leading to a breakthrough for un-supervised classification. It provides foundations for classifying big text data.
An integrated mathematical approach to synchronise and optimise hospital operations, 2014-2017
Human cues for robot navigation, 2014-2016
Browse our student topics