Learning strategies for personal agents to assist professional users in searching the Web. Many professional groups have large unmet information needs, with significant consequences for the public. We will take a novel strategy-based approach to the design of agents that assist humans in information search tasks, which represents a significant departure from the dominant paradigm of content-based retrieval. Our goal is to develop automated methods to learn task specific search strategies, embed ....Learning strategies for personal agents to assist professional users in searching the Web. Many professional groups have large unmet information needs, with significant consequences for the public. We will take a novel strategy-based approach to the design of agents that assist humans in information search tasks, which represents a significant departure from the dominant paradigm of content-based retrieval. Our goal is to develop automated methods to learn task specific search strategies, embed them in agents, and use them to guide human-agent interactions and search behaviours. To discover the effectiveness of our approach we will evaluate our methods with health care professionals.Read moreRead less
Practical methodologies for agent-oritented conceptual modelling. Conceptual modelling involves using knowledge representation techniques to support the requirements engineering phase of the software life-cycle. Agent-oriented conceptual modelling is a relatively new technique that offers significant benefits in modelling complex organisational information systems. However, several problems need to be addressed with current agent-oriented conceptual modelling languages and methodologies. In the ....Practical methodologies for agent-oritented conceptual modelling. Conceptual modelling involves using knowledge representation techniques to support the requirements engineering phase of the software life-cycle. Agent-oriented conceptual modelling is a relatively new technique that offers significant benefits in modelling complex organisational information systems. However, several problems need to be addressed with current agent-oriented conceptual modelling languages and methodologies. In the context of a PhD dissertation, this project will develop an improved agent-oriented conceptual modelling framework and related requirements elicitation techniques drawing on advances in Artificial intelligenct, Requireents Engineering and Organisational Semiotics. The practical deliverables of this project will address the needs of a large complex government organisation.Read moreRead less
Data Mining of Activity Transactions to Strengthen Debt Prevention. A national benefit from this research will be the significant analytical contribution to the prevention of incorrect payment directly associated with 30% of Commonwealth outlays. Funds not incorrectly paid will be available for direction to other areas of national importance. Another benefit is the new technology will have application in commercial, state and federal government agencies where research into activity, event or pro ....Data Mining of Activity Transactions to Strengthen Debt Prevention. A national benefit from this research will be the significant analytical contribution to the prevention of incorrect payment directly associated with 30% of Commonwealth outlays. Funds not incorrectly paid will be available for direction to other areas of national importance. Another benefit is the new technology will have application in commercial, state and federal government agencies where research into activity, event or process data can be used to improve service delivery outcomes. A further national benefit will be the development and use of frontier activity transaction mining techniques to ensure Australia a leading role in enterprise data mining research and development.Read moreRead less
Intelligent archiving and retrieving of clinic laboratory records in pathology/radiology informatics study. Pathology/radiology Informatics has emerged as an arm for developing next-generation pathology/radiology reporting methods, databases, imagery, and diagnostics. Current report archiving systems are very primitive, restricting any sophisticated use of the reports. This proposal aims to develop an innovative pathology/radiology report archiving system capable of automatically extracting usef ....Intelligent archiving and retrieving of clinic laboratory records in pathology/radiology informatics study. Pathology/radiology Informatics has emerged as an arm for developing next-generation pathology/radiology reporting methods, databases, imagery, and diagnostics. Current report archiving systems are very primitive, restricting any sophisticated use of the reports. This proposal aims to develop an innovative pathology/radiology report archiving system capable of automatically extracting useful information from reports. This system will make a smart use of pathology/radiology data and open a new way to extend current tests and examinations from being disease-focussed to being wellness focussed. It will also significantly reduce the number of tests, i.e., associated cost for healthcare.Read moreRead less
Intelligent archiving and retrieving of clinic laboratory records in pathology/radiology informatics study. Since 80% of the critical decisions made in medicine involve a pathology test or radiology examination, Pathology/radiology Informatics has emerged as an arm for developing next-generation pathology/radiology reporting methods, databases, imagery, and diagnostics. Current archiving systems are very primitive, restricting any sophisticated use of the reports. This proposal aims to collabora ....Intelligent archiving and retrieving of clinic laboratory records in pathology/radiology informatics study. Since 80% of the critical decisions made in medicine involve a pathology test or radiology examination, Pathology/radiology Informatics has emerged as an arm for developing next-generation pathology/radiology reporting methods, databases, imagery, and diagnostics. Current archiving systems are very primitive, restricting any sophisticated use of the reports. This proposal aims to collaborate with Lossless Data Compression Pty Ltd in developing an innovative pathology/radiology report archiving system capable of automatically extracting useful information. This system will make a smart use of pathology/radiology data and open a new way to extend current tests and examinations from being disease-focussed to being wellness focussed.Read moreRead less
Introducing computer-based documentation to Residential Aged Care: a multi-method evaluation of success. Improvements to quality and use of evidence-based methods in residential aged-care are restricted due to the very slow adoption of electronic information systems. This research will provide key investors, government, aged care providers and IT vendors, with tools to measure success in introducing IT into this sector. The project will create a platform with the national peak body, to dissemina ....Introducing computer-based documentation to Residential Aged Care: a multi-method evaluation of success. Improvements to quality and use of evidence-based methods in residential aged-care are restricted due to the very slow adoption of electronic information systems. This research will provide key investors, government, aged care providers and IT vendors, with tools to measure success in introducing IT into this sector. The project will create a platform with the national peak body, to disseminate lessons in successful implementation of computerised systems in residential aged-care, based on studies in two states. The studies will also benefit the international community researching technology adoption, by extending its boundary condition to a novel setting.Read moreRead less
An knowledge-based approach to multi-document text summarisation for automated meta-analysis of the scientific literature. The biomedical sciences produce literature at an exponential rate, and the size of this knowledge base far exceeds the capacity of humans to keep up with the growth in new knowledge. This project will develop computational text summarisation methods to abstract the content of scientific journal articles reporting clinical trials, and develop multi-document summarisation meth ....An knowledge-based approach to multi-document text summarisation for automated meta-analysis of the scientific literature. The biomedical sciences produce literature at an exponential rate, and the size of this knowledge base far exceeds the capacity of humans to keep up with the growth in new knowledge. This project will develop computational text summarisation methods to abstract the content of scientific journal articles reporting clinical trials, and develop multi-document summarisation methods to synthesise these abstracts using automated statistical meta-analysis methods. These methods have broad potential to improve text-summarisation technologies in general, to profoundly enhance our ability to integrate published knowledge, and to make a highly significant and specific contribution to improving the quality of evidence used in health decision-making. Read moreRead less
Sparse grid approximations and fitting using generalised combination techniques. Sparse grid techniques provide an effective tool to deal with the
computational curse of dimensionality which is a constant challenge in
modelling complex data. The proposed research is aimed at the
development and analysis of algorithms for data fitting with sparse
grids using variants of the combination technique. The outcome of the
research is a theory which will provide insights in the applicability,
limit ....Sparse grid approximations and fitting using generalised combination techniques. Sparse grid techniques provide an effective tool to deal with the
computational curse of dimensionality which is a constant challenge in
modelling complex data. The proposed research is aimed at the
development and analysis of algorithms for data fitting with sparse
grids using variants of the combination technique. The outcome of the
research is a theory which will provide insights in the applicability,
limitations and the convergence properties of the proposed
algorithms. The outcomes will be widely applicable in modelling of
large scale and complex data as is encountered in areas of
bioinformatics, physics and experimental studies of complex systems.
Read moreRead less
Generalised Linear Mixed Models: Theory, Methods and New Areas of Application. This project will aid the analysis of complex data sets throughout Australia. The ensuing methodology and software products will be applicable to data arising from longitudinal and geo-referenced public health and biomedical studies being conducted in Australia. It will also aid analysis of complex survey data from the Australian Bureau of Statistics and other agencies. Part of this project is geared towards smart inf ....Generalised Linear Mixed Models: Theory, Methods and New Areas of Application. This project will aid the analysis of complex data sets throughout Australia. The ensuing methodology and software products will be applicable to data arising from longitudinal and geo-referenced public health and biomedical studies being conducted in Australia. It will also aid analysis of complex survey data from the Australian Bureau of Statistics and other agencies. Part of this project is geared towards smart information use in Australian industries and will help foster collaboration between mathematical scientists and members of the Australian business sector. Cancer research in Australia will also benefit from this project.Read moreRead less
Cross-Community Information Systems: Understanding Technology-Practice Fit in Healthcare. This project addresses unsolved issues of usability of e-health information systems across diverse stakeholder communities that need to coordinate to deliver the expected revolution in patient-centred health care. The project will help realise the Nation's large investment in e-health by improving the likelihood of system acceptance, thus making a significant contribution to facilitating the important insti ....Cross-Community Information Systems: Understanding Technology-Practice Fit in Healthcare. This project addresses unsolved issues of usability of e-health information systems across diverse stakeholder communities that need to coordinate to deliver the expected revolution in patient-centred health care. The project will help realise the Nation's large investment in e-health by improving the likelihood of system acceptance, thus making a significant contribution to facilitating the important institutional transformations expected of these systems. The timeliness, depth and breadth of the study will yield outcomes that will enhance Australia's research reputation. This project directly addresses the 'smart information use' and 'promoting and maintaining good health' national research prioritiesRead moreRead less