Towards automated and intelligent processing of web-based information. The successful outcome of this project will enhance Australia's research reputation in an important, practical area of ICT, will contribute to emerging Web standards, will produce frontier technology that will eventually be of benefit to Australian industry, and will train several postgraduate students.
Personalised Content Delivery for Assisted Navigation of Information Rich, Physical Environments such as a Museum. The research will yield improved international standing through scientific advances disseminated through high impact refereed publications and open source software. The collaborations within the project will make Melbourne a hub for research in user modeling and language technology. This will attract post-graduate students in these areas, and potentially commercialisation interest. ....Personalised Content Delivery for Assisted Navigation of Information Rich, Physical Environments such as a Museum. The research will yield improved international standing through scientific advances disseminated through high impact refereed publications and open source software. The collaborations within the project will make Melbourne a hub for research in user modeling and language technology. This will attract post-graduate students in these areas, and potentially commercialisation interest. The demonstration prototypes will provide proof of concept of eventual applications that improve the capabilities of the environments in which we live. These applications, which can be investigated by follow-up projects, will in turn encourage collaborations with Australian companies seeking to build innovative software applications.Read moreRead less
Supporting adaptive, interactive documents. The project will improve comprehensibility of technical material, reduce paper usage, encourage collaborative science, improve the reliability of published science (by allowing post-publication annotation and correction), and improve the accessibility of technical material for readers who are blind or have poor vision. The project also holds considerable potential for supporting Australian companies in the publishing and document processing industries.
Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected ....Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected outcomes include the
development of software that allows the solution of hitherto unsolved machine
learning problems, and the ability to solve problems larger than those solvable
by the current generation of machine learning tools.Read moreRead less
Model-based error location in Java programs. The construction of modern software requires extensive testing and
debugging in addition to using appropriate specification, design, and
verification techniques. Testing and debugging are very time-consuming
and costly, drawing - according to recent articles - "typically 50%
or more of the resources for software projects''. By providing a new,
flexible approach to the debugging of complex software, this project
offers the potential of significant cost ....Model-based error location in Java programs. The construction of modern software requires extensive testing and
debugging in addition to using appropriate specification, design, and
verification techniques. Testing and debugging are very time-consuming
and costly, drawing - according to recent articles - "typically 50%
or more of the resources for software projects''. By providing a new,
flexible approach to the debugging of complex software, this project
offers the potential of significant cost savings, highly beneficial to
the ICT industry. Lessons learned from the demonstration prototype,
can be directly carried over into commercial tool development. In
addition, the project strengthens links to high quality European
research laboratories.Read moreRead less
Parallel and Distributed Machine Learning - Smart Data Analysis in the Multicore Era. In large data centres our research will lead to reduced energy consumption by using graphics cards which have a much better computation to power ratio than traditional processors. On desktop computers, it will make machine learning practical by enabling efficient algorithms for spam filtering and content analysis. On networked systems it will lead to distributed inference, caching and collaborative filtering ap ....Parallel and Distributed Machine Learning - Smart Data Analysis in the Multicore Era. In large data centres our research will lead to reduced energy consumption by using graphics cards which have a much better computation to power ratio than traditional processors. On desktop computers, it will make machine learning practical by enabling efficient algorithms for spam filtering and content analysis. On networked systems it will lead to distributed inference, caching and collaborative filtering applications which will both reduced the bandwidth required and make the internet safer for users. Finally, it will enable rapid deployment of sensor networks for monitoring and detection, such as for environmental monitoring and safeguarding Australia's borders.Read moreRead less
Combining modal logics for dynamic and multi-agent systems. Modern computer software systems are required to operate in complex dynamic environments and to handle functioning of highly sensitive (security and safety-critical) organizations in government and commerce. Typical applications include air-traffic control systems, telecommunication networks, and banking systems. To ensure robustness, computationally predictable behaviour and trustworthiness of these systems, their designs and implement ....Combining modal logics for dynamic and multi-agent systems. Modern computer software systems are required to operate in complex dynamic environments and to handle functioning of highly sensitive (security and safety-critical) organizations in government and commerce. Typical applications include air-traffic control systems, telecommunication networks, and banking systems. To ensure robustness, computationally predictable behaviour and trustworthiness of these systems, their designs and implementations must be formally well grounded. This is an important but difficult challenge. This project will systematically develop a framework by combining modal-logics to adequately capture and reason about temporal, epistemic and social aspects of dynamic and multi-agent systems. The combined logics would be evaluated on practical applications.
Read moreRead less
Intention Selection in Intelligent Agent Systems. Although intelligent multi-tasking is the foundation of rational behaviour, very little work has been done to date. Work in this area will maintain Australia's reputation of being at the forefront of work in Intelligent Agents. It will also provide a basis which can later be further developed for inclusion in applications and agent platforms. Australia has a number of companies, such as Agent Oriented Software, and government organisations, such ....Intention Selection in Intelligent Agent Systems. Although intelligent multi-tasking is the foundation of rational behaviour, very little work has been done to date. Work in this area will maintain Australia's reputation of being at the forefront of work in Intelligent Agents. It will also provide a basis which can later be further developed for inclusion in applications and agent platforms. Australia has a number of companies, such as Agent Oriented Software, and government organisations, such as the Bureau of Meteorology and the Department of Defence, which use agent technology. These companies would benefit from this work as it would tackle a long-standing key problem in the area of intelligent systems.Read moreRead less
Complexity Measures Of Design Spaces As Basis For Mass Customisation Of Novel Designs. This project aims to develop, implement and test a means to determine the potential of any arbitrary design generator to produce a diversity of designs and to utilise that means to control the mass customisation of novel designs. Globalisation of markets has produced the need to be able to mass customise designs that are not simple variants of existing designs. Any improvement in Australia's capacity to provid ....Complexity Measures Of Design Spaces As Basis For Mass Customisation Of Novel Designs. This project aims to develop, implement and test a means to determine the potential of any arbitrary design generator to produce a diversity of designs and to utilise that means to control the mass customisation of novel designs. Globalisation of markets has produced the need to be able to mass customise designs that are not simple variants of existing designs. Any improvement in Australia's capacity to provide this service will improve both its internal efficiency and increase its competitiveness in the increasing international marketplace for designing through the production of the basis for a new class of designing tools.Read moreRead less
Pattern Recognition and Scene Analysis via Machine Learning. We plan to use kernel methods, a novel machine learning technique, for computer vision problems, such as scene analysis and real time object recognition. Such capabilities are relevant for the design of intelligent and adaptive systems, suitable for complex real world environments. Expected outcomes are the design of efficient statistical tools which take the special nature of visual data into account (structure, decomposition, prior ....Pattern Recognition and Scene Analysis via Machine Learning. We plan to use kernel methods, a novel machine learning technique, for computer vision problems, such as scene analysis and real time object recognition. Such capabilities are relevant for the design of intelligent and adaptive systems, suitable for complex real world environments. Expected outcomes are the design of efficient statistical tools which take the special nature of visual data into account (structure, decomposition, prior knowledge of physical environments, etc.) and combine the advantages of feature based high-level vision methods with low-level machine learning techniques.
This proposal is part of a joint IST project with partners from the European Union.Read moreRead less