Completed ARC Discovery Projects

Summaries of Completed ARC Discovery Projects

A compositional model for verifying and programming ecologies of smart Internet devices
ARC Discovery 2004-2006
Dr S. Loke; Dr S Ling
Emerging in 21st century computing is what we perceive as device ecologies, or collections of devices that can exhibit smart behaviour, automate tasks, interact synergistically with one another, with users and Internet resources, and provide aid and value in daily life and work. Device ecologies will be seen in areas as diverse as e-commerce, health care, home automation, office automation, manufacturing, and defense. This project will develop a novel model and language for analyzing and programming device ecologies. This will be an Australian contribution towards techniques for constructing advanced applications that work over the computing infrastructure of the future.

Advanced bayesian networks for epidemiology
ARC Discovery 2004-2006
Dr K. Korb, Prof J. McNeil, Dr A. Nicholson and Prof R. Neopolitan
We will demonstrate the potential of advanced Artificial Intelligence for medical informatics by extending the capabilities of Bayesian Networks. Bayesian Networks excel when researchers need to combine causal and diagnostic reasoning in areas characterised by uncertainty. But they have one flaw which hinders their use: they do not yet easily mix continuous and discrete variables. We will extend them to handle such mixes, then demonstrate how much they can improve on current methods for predicting, among other things, coronary heart disease (CHD)

Concept-based multilingual web content mining
ARC Discovery 2004-2006
A/Prof C. Yeh; A/Prof K. Smith; Dr R. Chau [APD]
Towards smart use of Web information, this pioneer project will develop an innovative concept-based approach for discovering global knowledge embedded within multilingual Web documents. Departing from the traditional bilingual term-to-term machine translation techniques, the approach overcomes the notorious vocabulary mismatch problem by enabling synchronised lexical mapping of multiple languages. A series of intelligent concept-based techniques using fuzzy logic and neural networks will be investigated to support smart Web information browsing and exploration. This project will provide valuable new insights into developing state-of-the-art multilingual Web mining applications for enhancing business intelligence in Australia 's knowledge driven industries.

Emergence of modular structure in complex systems
ARC Discovery 2004-2006
Prof DG Green
Complex systems pervade our world, but are still poorly understood. Self-contained modules provide the most widespread and effective way of reducing and managing complexity, but the way they form in natural systems remains largely a mystery. This study investigates mechanisms that contribute to module formation in complex networks, including adaptation, clustering, enslavement, feedback, phase change and synchronisation. Outcomes will include insights into the organisation and functioning of many complex systems, including the Internet, ecological communities and genetic networks. Practical outcomes will include new modelling tools and applications both to evolutionary computation and the design and control of large information networks.

Extending association rule discovery to numeric data
ARC Discovery 2004-2006
Prof GI Webb
This project tackles a key limitation of association-rule discovery, which is one of the main techniques used in data mining. Much valuable data is numeric. However, association-rule discovery cannot satisfactorily model numeric data, a limitation that has greatly restricted its application. This project investigates a novel new technique that overcomes this limitation. Impact-rule discovery finds associations with numeric distributions. This allows data analysts to discover precisely the type of information that they usually seek from numeric data, for example, how to maximize either average or aggregate measures of outcomes such as health, compliance, profit, or accuracy.

One day, we'll all invest this way! Regulating Online investment
ARC Discovery 2005-2007
Prof D. Kingsford Smith, Dr K. Williamson, Dr K. Ting
This project will provide policy recommendations to promote national research priority 3: particularly goals 4 & 5. It will do this by using good regulation to increase the safety of online investing services. It will bring to Australia international expertise not available here, crucial to good regulation of online investing. If investors trust this mostly beneficial technology it will further Australians' prosperity through investment e.g. for retirement. Competitive advantage through good regulation will bring overseas investors to Australia through the Internet. It will consolidate its role as a financial centre. With 51% of adults owning shares, this research could save Australians more than $1.6 billion per annum.

Resource-bounded adaptive inference of accurate conditional probability estimates from data
ARC Discovery 2005-2007
Prof G. Webb; Dr K. Korb; Dr K. Ting
This project will develop machine learning techniques with a valuable new capability: the ability to produce estimates of complex conditional probabilities to varying levels of expected accuracy depending upon the constraints of available computational resources. This will provide significant competitive advantage to developers of many types of online application by allowing them to maximise utilisation of available computational resources when making inferences from data, together with the flexibility to trade-off accuracy and computing resources during system design. Australia will also benefit by strengthening its machine learning expertise, which is central to many complex and intelligent systems and the booming data mining industry.

Socio-technical determinants of agile, network-centre organisations
ARC Discovery 2005-2007
A/Prof H. Hasan (University of Wollongong), Dr K. Crawford (Novae Research), Dr D. Hart (ANU), Dr H. Linger, Dr L. Warne (Department of Defence) and Ms I. Ali (Department of Defence)
Many companies provide value for customers by exploiting information and communication technology in support of networks of self-organising employee teams. Such network-centric approaches to organisational structure and function are becoming desired in diverse government organisations and societal settings. On one hand, the civil society is increasing reliant on virtual networks and online communities. On the other, the military's imperative to learn how to fight smarter in the information age heralds a fundamental shift from platform-centred warfare to a mode with diffuseness of command and control. The findings of this research will enable the potential benefits of network- centrism to be realised in these nationally critical areas.

  
Research grants links