A Commercially Viable, Innovative XML - Enabled Association Rule Framework. The pervasive nature of the Web has raised two important issues, namely (1) how to exchange data between isolated information systems within two different companies with their own data formats and (2) how to store information particularly documents, so that they can be accessed through the internet based on their meaning. The Extended Markup Language XML has emerged as the favoured means of addressing these issues and th ....A Commercially Viable, Innovative XML - Enabled Association Rule Framework. The pervasive nature of the Web has raised two important issues, namely (1) how to exchange data between isolated information systems within two different companies with their own data formats and (2) how to store information particularly documents, so that they can be accessed through the internet based on their meaning. The Extended Markup Language XML has emerged as the favoured means of addressing these issues and this is leading to an explosive growth in the information stored in this way. This project addresses the issue of determination of patterns and knowledge in information stored in XML through datamining.Read moreRead less
Mining Multiple Information Sources through Collaborative and Comparative Analysis. Mining multiple information sources can significantly enhance our capacity for smart information use. This is because patterns behind scams, fraud, and terrorism activities are difficult to detect, unless pieces of isolated information are properly linked together for mining. This project will deliver cutting-edge data mining techniques, actionable tools, and case study materials, all of which will lead to a numb ....Mining Multiple Information Sources through Collaborative and Comparative Analysis. Mining multiple information sources can significantly enhance our capacity for smart information use. This is because patterns behind scams, fraud, and terrorism activities are difficult to detect, unless pieces of isolated information are properly linked together for mining. This project will deliver cutting-edge data mining techniques, actionable tools, and case study materials, all of which will lead to a number of high quality publications to enhance Australia's international foremost standing in the data mining community. The project will involve highly trained and skilled researchers and practitioners to advance the workforce development in the Australian information technology industry and ensure the healthy growth of the economy.Read moreRead less
Formal Context Analysis in Rapidly Evolving Knowledge Webs (4CARE-K). On-the-fly personalised assembly of complex objects (learning
materials, contracts, plans, designs, software configurations, etc)
is increasingly expected in knowledge processing and decision
making. This requires the discovery of discrete underlying models and
taxonomies of subject domains and statistical matching in dynamically
varying contexts defined by changing personal preferences, tasks,
objectives and other chara ....Formal Context Analysis in Rapidly Evolving Knowledge Webs (4CARE-K). On-the-fly personalised assembly of complex objects (learning
materials, contracts, plans, designs, software configurations, etc)
is increasingly expected in knowledge processing and decision
making. This requires the discovery of discrete underlying models and
taxonomies of subject domains and statistical matching in dynamically
varying contexts defined by changing personal preferences, tasks,
objectives and other characteristics. This project addresses formal
models of context and similarity based in applied lattice theory
(formal concepts), feature logic and statistical retrieval. Parallel
algorithms will be developed, analysed and benchmarked to enable
high-performance processing of vast numbers of heterogeneous objects
in a distributed knowledge web.Read moreRead less
Efficient and Effective Text Information Retrieval with Phrases. Current Internet search engines find documents by matching queries to documents, then present the closest matches to the user. Such searching is often ineffective. Another technique for searching, which with current algorithms is not feasible for large text collections such as the Web, is to browse vocabularies and view phrases in the contexts in which they are used. The aim of this project is to make wider use of phrases in re ....Efficient and Effective Text Information Retrieval with Phrases. Current Internet search engines find documents by matching queries to documents, then present the closest matches to the user. Such searching is often ineffective. Another technique for searching, which with current algorithms is not feasible for large text collections such as the Web, is to browse vocabularies and view phrases in the contexts in which they are used. The aim of this project is to make wider use of phrases in retrieval, by developing new phrase-based querying algorithms and investigating how users can use phrase indexes to find documents. The outcome will be new, efficient methods for exploring the Internet.Read moreRead less
Building a Prototype for Quality Information Retrieval from the Internet. This projects aims to consider fundamental issues in implementing a prototype quality information retrieval system from the world wide web. These issues include: retrieval of relevant pages to a given topic using a focussed crawler; text categorisation of the retrieved web pages; quality selection criteria with the formulation of a quality index to determine quality of retrieved pages, and user interface design to obtain r ....Building a Prototype for Quality Information Retrieval from the Internet. This projects aims to consider fundamental issues in implementing a prototype quality information retrieval system from the world wide web. These issues include: retrieval of relevant pages to a given topic using a focussed crawler; text categorisation of the retrieved web pages; quality selection criteria with the formulation of a quality index to determine quality of retrieved pages, and user interface design to obtain relevance feedback. The outcome will be a prototype system useful to business and industry though to guide our thinking we will use issues in constructing a quality digital library collection as a sounding board.
Read moreRead less
Beamforming with acoustic vector sensors for audio user interfaces. We aim to create new Audio User Interfaces (AUIs) for the automatic separation and annotation of audio from complex sound scenes using acoustic vector sensor beamforming technology. Specifically, we will develop: speech AUIs for noisy, multi-talker, reverberant environments; and sound transcription AUIs for the deaf. Ultimately, users will be able to walk into a room, hold conversations and leave with a searchable, automatically ....Beamforming with acoustic vector sensors for audio user interfaces. We aim to create new Audio User Interfaces (AUIs) for the automatic separation and annotation of audio from complex sound scenes using acoustic vector sensor beamforming technology. Specifically, we will develop: speech AUIs for noisy, multi-talker, reverberant environments; and sound transcription AUIs for the deaf. Ultimately, users will be able to walk into a room, hold conversations and leave with a searchable, automatically-generated transcript of the audio events, tagged with metadata. The application of these technologies will create new possibilities for recording audio in the music, radio, TV industries, and future home based audio communication systems.Read moreRead less
Investigation and development of robust rule discovery and classification system. This research focuses on a national research priority, namely smart information use. The expected outcomes of the project will greatly advance intelligent system design, such as automatic decision making, fault detection and problem diagnosis, for finance, medical, telecom and many other areas. It has great potential for commercialisation and earning incomes for the future research. The publications will benefit th ....Investigation and development of robust rule discovery and classification system. This research focuses on a national research priority, namely smart information use. The expected outcomes of the project will greatly advance intelligent system design, such as automatic decision making, fault detection and problem diagnosis, for finance, medical, telecom and many other areas. It has great potential for commercialisation and earning incomes for the future research. The publications will benefit the future development of intelligent systems for dealing with missing data. This project directly supports a PhD student and two research assistants who will most likely continue their higher degree study. These contribute to regional tertiary education.Read moreRead less
A Generic Software Architecture for Web-Based Applications on Micro-Mobile Systems. The next generation of computers that will capture the imagination of the society are likely to be micro-mobile devices such as personal digital assistants, mobile phones, smartcards and chips embedded in home and office items. Developing applications for information processing using a wireless network of such devices is an emerging challenge. This project will develop and evaluate a generic architecture for web- ....A Generic Software Architecture for Web-Based Applications on Micro-Mobile Systems. The next generation of computers that will capture the imagination of the society are likely to be micro-mobile devices such as personal digital assistants, mobile phones, smartcards and chips embedded in home and office items. Developing applications for information processing using a wireless network of such devices is an emerging challenge. This project will develop and evaluate a generic architecture for web-based applications on micro-mobile devices. This will make it easy to design applications that can seamlessly interact with different kinds of devices. The project will be carried out in partnership with Total Internet Centre, a Newcastle based regional enterprise.Read moreRead less
Multi-resolution spatial query processing. The cost of spatial query processing is directly related to spatial data complexity and accuracy. While spatial data is often stored in a database with the highest level of detail available, not all applications require the same level of detail. Recognising the difficulties of multiple representations of spatial data, in this project we propose to use multi-resolution data structures as a new foundation for efficient, application-dependent, on-demand de ....Multi-resolution spatial query processing. The cost of spatial query processing is directly related to spatial data complexity and accuracy. While spatial data is often stored in a database with the highest level of detail available, not all applications require the same level of detail. Recognising the difficulties of multiple representations of spatial data, in this project we propose to use multi-resolution data structures as a new foundation for efficient, application-dependent, on-demand derivation of data at different resolution levels. The systematic approach adopted in this project has the potential to deliver performance improvement that previous algorithm-level-only research cannot match.Read moreRead less
Fast and Scalable Search Techniques for Genomic Databases. Tens of thousands of users each day search the genomic databases that are so far the most significant product of the Human Genome Project. In this project, we will investigate fundamental new bioinformatics techniques for information retrieval from genomic databases. The outcomes will allow molecular biologists to accurately and efficiently discover relationships between DNA and protein sequences. In contrast to existing approaches, o ....Fast and Scalable Search Techniques for Genomic Databases. Tens of thousands of users each day search the genomic databases that are so far the most significant product of the Human Genome Project. In this project, we will investigate fundamental new bioinformatics techniques for information retrieval from genomic databases. The outcomes will allow molecular biologists to accurately and efficiently discover relationships between DNA and protein sequences. In contrast to existing approaches, our techniques will remain fast despite the enormous growth in genomic database sizes. This research will contribute significantly to the "key areas of study includ[ing] genomics and bioinformatics" in the new ARC genome/phenome link priority area.Read moreRead less