Investigations into machine learning applications in link analysis. Link analysis is an emerging tool for the detection of patterns in structured data. The detection of pattern in such data can lead to the detection of fraud occurrence, security breaches in computer systems, and patterns of social interactions with a community. It is also popularly applied to applications such as Web search engine designs and marketing analysis. This project aims to advance the area of link analysis by allowing ....Investigations into machine learning applications in link analysis. Link analysis is an emerging tool for the detection of patterns in structured data. The detection of pattern in such data can lead to the detection of fraud occurrence, security breaches in computer systems, and patterns of social interactions with a community. It is also popularly applied to applications such as Web search engine designs and marketing analysis. This project aims to advance the area of link analysis by allowing the incorporation of contextual information which accounts for relationships among actors properly. Advances in link detection will allow improvements in security and Web services on which a wide field of national bodies rely. This project can help to place Australia at the forefront of this research area.Read moreRead less
Ask the Net: Intelligent Natural Language Learning. Natural Language Processing (NLP) has progressed rapidly using corpus-based machine learning techniques. However, corpus development costs cause a ?data bottleneck? which prevents systems from reaching human competence. This project overcomes the difficulties of creating huge corpora by employing the innate language ability of untrained contributors. We will show how to automatically select and present examples, containing informative lingui ....Ask the Net: Intelligent Natural Language Learning. Natural Language Processing (NLP) has progressed rapidly using corpus-based machine learning techniques. However, corpus development costs cause a ?data bottleneck? which prevents systems from reaching human competence. This project overcomes the difficulties of creating huge corpora by employing the innate language ability of untrained contributors. We will show how to automatically select and present examples, containing informative linguistic structures, which are most beneficial for training NLP systems. These examples will be analysed by many contributors whose responses will be automatically collated into corpora. Huge corpora are vital to emerging language technologies for managing textual information in the global economy.
Read moreRead less
Data Exchange and Service Integration with Applications in Health Information Systems. This project will research and develop an innovative new approach to facilitate real data exchange and service integration across different medical organisations. This approach will significantly improve the quality of health care by providing a solid foundation for integrated medical services, offering on demand and effective access to fragmentally stored patients medical information and minimise the number o ....Data Exchange and Service Integration with Applications in Health Information Systems. This project will research and develop an innovative new approach to facilitate real data exchange and service integration across different medical organisations. This approach will significantly improve the quality of health care by providing a solid foundation for integrated medical services, offering on demand and effective access to fragmentally stored patients medical information and minimise the number of data entry errors injected into the medical information systems. The novel integration model will also enable a new autonomous approach for demographic data collection which is essential for evidenced resource allocation, policy making and disease prevention.Read moreRead less
Defence Against Phishing Attacks. Australian businesses and citizens are losing millions of dollars in cybercrimes every year. Rural and regional businesses depend on the integrity of their Internet banking service, and yet, cybercriminals are working hard to defraud these users. This project aims to build a reliable defence against phishing attacks which rely on social engineering to steal online identities, using intelligence gathered from the brazen trade of credentials in the public domain.
Geospatial Information Processing for Quickbird Satellite Imagery. Of the new generation of commercial high-resolution earth observation satellites, the Quickbird system with its 70cm resolution has greatest potential for metric applications. The capabilities of Quickbird imagery for digital mapping, GIS and geopositioning are, however, yet to be fully established and the models, procedures and computational systems required for higher-accuracy applications require further research. The aim of t ....Geospatial Information Processing for Quickbird Satellite Imagery. Of the new generation of commercial high-resolution earth observation satellites, the Quickbird system with its 70cm resolution has greatest potential for metric applications. The capabilities of Quickbird imagery for digital mapping, GIS and geopositioning are, however, yet to be fully established and the models, procedures and computational systems required for higher-accuracy applications require further research. The aim of this project, which is a collaboration with SKM, is to develop the tools necessary to validate Quickbird imagery as a source for geospatial information collection, to develop the associated data processing systems to proof-of-concept stage and to experimentally verify these systems.Read moreRead less
Extending association rule discovery to numeric data. 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. ....Extending association rule discovery to numeric data. 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.Read moreRead less
User-Driven Composition of Web Services. Web service composition technology promises to revolutionise the way in which organisations interact over the Web. However existing environments for the composition of Web services are too complex to use and are usually intended for experienced application developers as they rely either on scripting languages, or on a process-modelling notations intended to be used by IT experts. However, the need for customised composition of Web services is likely to em ....User-Driven Composition of Web Services. Web service composition technology promises to revolutionise the way in which organisations interact over the Web. However existing environments for the composition of Web services are too complex to use and are usually intended for experienced application developers as they rely either on scripting languages, or on a process-modelling notations intended to be used by IT experts. However, the need for customised composition of Web services is likely to emanate from non IT-experts.
The project aims at designing, implementing, and evaluating an environment for the specification and execution of composite Web services by non-expert.Read moreRead less
Privacy-preserving Web Services Composition. Web services composition is emerging as a promising technology for the
effective automation of business-to-business collaborations. It allows
organizations to form alliances by connecting their applications and systems, in order to offer ``one-stops shops'' for their customers. However, several important issues (e.g., security and privacy) need to be properly addressed before Web services technology meets the requirements of critical applications s ....Privacy-preserving Web Services Composition. Web services composition is emerging as a promising technology for the
effective automation of business-to-business collaborations. It allows
organizations to form alliances by connecting their applications and systems, in order to offer ``one-stops shops'' for their customers. However, several important issues (e.g., security and privacy) need to be properly addressed before Web services technology meets the requirements of critical applications such as e-goverment. This project aims at providing privacy preserving Web services composition techniques. The anticipated outcome of this project is a service composition framework that provides seamless interoperability between different Web services without violiating citizens and organisations privacy.Read moreRead less
Design-Driven Requirements for Internet-Enabled System Development. The nature of Web system development is significantly different from conventional, software and IT development. Amongst other factors, there is substantial uncertainty in both clients' understanding of their needs and developers' understanding of the systems domain. We will develop an uncertainty model relevant to the development model relevant to the development of internet-enabled systems, and then use this model to adapt th ....Design-Driven Requirements for Internet-Enabled System Development. The nature of Web system development is significantly different from conventional, software and IT development. Amongst other factors, there is substantial uncertainty in both clients' understanding of their needs and developers' understanding of the systems domain. We will develop an uncertainty model relevant to the development model relevant to the development of internet-enabled systems, and then use this model to adapt the design process to support elicitation of requirements, as well as developing support for this adapted process. This will facilitate the development of systems that more accurately reflect clients' needs, and result in an understanding of what would be involved in reducing development costs.Read moreRead less
Supporting co-evolution of business processes and Web systems. This research will provide significant benefit to the Australian Internet and e-commerce industries (valued by the ABS as in excess of $11b/year). It will result in improved products that better satisfy specific business needs (and hence improved competitiveness in a global market). Development cycles will shorten (as the likelihood of redevelopment decreases) and costs of development will fall. Finally, the models and tools to be ....Supporting co-evolution of business processes and Web systems. This research will provide significant benefit to the Australian Internet and e-commerce industries (valued by the ABS as in excess of $11b/year). It will result in improved products that better satisfy specific business needs (and hence improved competitiveness in a global market). Development cycles will shorten (as the likelihood of redevelopment decreases) and costs of development will fall. Finally, the models and tools to be developed will facilitate the transition of traditional organisations into the new economy, as the outcomes of this research will provide a transparent cost-effective approach for identifying and clarifying the evolving business domain and the requirements of companies.Read moreRead less