Varying similarity metrics in indexing and retrieving high dimensional data. Many applications require varying distance metrics by putting a weight on different dimensions. Taking an example in visual information retrieval, due to the subjective nature of similarity measurements, the distance metrics can vary between different users. The main problem with k nearest neighbour (k-nn) searches using weighted metrics in a high dimensional space is whether the searches can be done efficiently, since ....Varying similarity metrics in indexing and retrieving high dimensional data. Many applications require varying distance metrics by putting a weight on different dimensions. Taking an example in visual information retrieval, due to the subjective nature of similarity measurements, the distance metrics can vary between different users. The main problem with k nearest neighbour (k-nn) searches using weighted metrics in a high dimensional space is whether the searches can be done efficiently, since in an arbitrary distance metric the intersection between the k-nn sphere and the bounding envelopes of nodes in an index tree cannot be easily calculated. This project aims to seek a novel solution. It will create a great impact on and have many applications in high dimensional visual information retrieval, instance-based learning, complex analysis, non-parametric density estimation, etc.Read moreRead less
Managing and Mining Evolving Ontologies through combining Patterns Languages and Data Mining. Data mining offers insight into the substantial and growing repositories of medical data while pattern languages offer the ability to provide a high level conceptual designs of an artifact or process. This project thus promises to facilitate, on the one hand, the discovery of medical knowledge from large quantities of clinical or epidemiological data, while also providing a better way of constructing a ....Managing and Mining Evolving Ontologies through combining Patterns Languages and Data Mining. Data mining offers insight into the substantial and growing repositories of medical data while pattern languages offer the ability to provide a high level conceptual designs of an artifact or process. This project thus promises to facilitate, on the one hand, the discovery of medical knowledge from large quantities of clinical or epidemiological data, while also providing a better way of constructing and validating medically oriented design patterns which can then be used in medical data collection systems.Read moreRead less
Special Research Initiatives - Grant ID: SR0354696
Funder
Australian Research Council
Funding Amount
$30,000.00
Summary
ARC Research Network in Enterprise Information Infrastructure (EII). This research network targets investigation of Enterprise Computing and its infrastructure, with an emphasis on emerging advanced technologies and practices, for large-scale enterprises, government agencies and community groups. EII will bring together the best IT researchers, leading edge users and key IT technology providers to support consolidated, technically sound, integrated and strategically positioned research towards s ....ARC Research Network in Enterprise Information Infrastructure (EII). This research network targets investigation of Enterprise Computing and its infrastructure, with an emphasis on emerging advanced technologies and practices, for large-scale enterprises, government agencies and community groups. EII will bring together the best IT researchers, leading edge users and key IT technology providers to support consolidated, technically sound, integrated and strategically positioned research towards solutions for next generation Enterprise Computing. Web services, the Semantic Web and Service Oriented Computing are fast emerging new disciplines with far reaching impacts. EII will contribute to their growth and to their practical deployment in Australia and beyond. The establishment of EII network will dramatically add value to already supported but often fragmented research projects.Read moreRead less
The Quantum Mechanics of Semantic Space. Quantum mechanics (QM) is a well known and successful theory from physics which has recently attracted quite some public interest. Quantum Mechanics is emerging out of physics and permeating into other areas, for example, information retrieval, human language and cognition. This offers tantalizing possibilities and bizarre implications, some of which, if realized, can lead to genuine breakthroughs in producing information technology to enhance human aware ....The Quantum Mechanics of Semantic Space. Quantum mechanics (QM) is a well known and successful theory from physics which has recently attracted quite some public interest. Quantum Mechanics is emerging out of physics and permeating into other areas, for example, information retrieval, human language and cognition. This offers tantalizing possibilities and bizarre implications, some of which, if realized, can lead to genuine breakthroughs in producing information technology to enhance human awareness in increasingly complex information environments. Through this project, Australia has the possibility to be at the forefront and have a hand in determining such developments.Read moreRead less
Exploiting Views in Extensible Markup Language (XML) Data Processing. This project addresses an important technical issue in smart information use, which is among Australian National Research Priorities. The techniques developed in this project will enable Australian organizations to build smarter and more efficient information systems, hence making them more competitive in the global market. The problems in this project are technically challenging, solving them in Australia will enhance Austr ....Exploiting Views in Extensible Markup Language (XML) Data Processing. This project addresses an important technical issue in smart information use, which is among Australian National Research Priorities. The techniques developed in this project will enable Australian organizations to build smarter and more efficient information systems, hence making them more competitive in the global market. The problems in this project are technically challenging, solving them in Australia will enhance Australia's international research reputation. The project will also boost Australia's research capability by training PhD and honours students.
Read moreRead less
Comparative analysis and exploration of collections of data clusterings. Data clustering is an important technique for extracting knowledge from complex datasets. It is widely used by Australian science, government and industry, in areas such as genomics, proteomics, crime analysis, marketing and customer profiling. This project will develop new techniques that will allow users to explore and analyse collections of data clusterings. This will improve the current generation of clustering softw ....Comparative analysis and exploration of collections of data clusterings. Data clustering is an important technique for extracting knowledge from complex datasets. It is widely used by Australian science, government and industry, in areas such as genomics, proteomics, crime analysis, marketing and customer profiling. This project will develop new techniques that will allow users to explore and analyse collections of data clusterings. This will improve the current generation of clustering software and allow deeper investigation of challenging and complex data.
Read moreRead less
A scheme of local compilation of mobile collectors for image and video search engines. The object collector is an important component in a Web search engine. A collector collects Web objects (text, image, video, etc), extracts their features and builds an index file for the search engine. Sending each object to the collector is always the worst option with respect to resource usage because it is the feature, not the entire object, which will be used in indexing and retrieval. An alternative is t ....A scheme of local compilation of mobile collectors for image and video search engines. The object collector is an important component in a Web search engine. A collector collects Web objects (text, image, video, etc), extracts their features and builds an index file for the search engine. Sending each object to the collector is always the worst option with respect to resource usage because it is the feature, not the entire object, which will be used in indexing and retrieval. An alternative is to send a collector to the source site, which has an advantage of distributing computational load and performing summarization and compression. This project proposes a locally compiled mobile collector for image and video search engines.Read moreRead less
Coordinated and Cooperative Load Sharing between Content Delivery Networks. Popular web services can experience severe downtimes as the result of heavy traffic. Enabling coordinated and cooperative content delivery between existing Content Delivery Networks (CDNs) will allow a CDN provider to rapidly 'scale-out' without investing in new infrastructure, to meet both flash crowds and anticipated increases in demand. Improved cost effectiveness, performance and locality for providers and end-users ....Coordinated and Cooperative Load Sharing between Content Delivery Networks. Popular web services can experience severe downtimes as the result of heavy traffic. Enabling coordinated and cooperative content delivery between existing Content Delivery Networks (CDNs) will allow a CDN provider to rapidly 'scale-out' without investing in new infrastructure, to meet both flash crowds and anticipated increases in demand. Improved cost effectiveness, performance and locality for providers and end-users can be achieved by leveraging existing infrastructure provided by other CDNs, creating economies of scale that were previously impossible. This is crucial for uses on the so-called edges of the internet (e.g. Australia) that depend on a small number of expensive data links to the major data centres in Europe and the USA.Read moreRead less
PreferPeer: Towards Efficient Location-aware Preference Search in Mobile Peer-to-Peer Databases. Our research is right in the forefront of ICT research, leading the international effort of extending database technologies to support data management and query processing in very large scale highly mobile data. The proposed PreferPeer stands to open up major research directions in mobile point-to-point computing. Advances in this project will bring significant economic and social benefits to Austral ....PreferPeer: Towards Efficient Location-aware Preference Search in Mobile Peer-to-Peer Databases. Our research is right in the forefront of ICT research, leading the international effort of extending database technologies to support data management and query processing in very large scale highly mobile data. The proposed PreferPeer stands to open up major research directions in mobile point-to-point computing. Advances in this project will bring significant economic and social benefits to Australia. The research outcome of this project will directly benefit the following sectors: telecommunications, transportation, supply chain management, logistics, mobile computing, mobile e-commerce and marketing, air traffic control, defence, and so on, where efficient access to large amounts of highly mobile and distributed information is vital.Read moreRead less
Efficient Similarity Query Processing in High Dimensional Databases. This project studies a fundamental problem common to a wide range of applications. It contributes to smart use of information, which is vital to the modern knowledge-based economy, by providing an enabling technology to capitalise Australia's huge investment in data collection. Our research is right in the forefront of ICT research, leading the international effort of extending database technologies to support data management a ....Efficient Similarity Query Processing in High Dimensional Databases. This project studies a fundamental problem common to a wide range of applications. It contributes to smart use of information, which is vital to the modern knowledge-based economy, by providing an enabling technology to capitalise Australia's huge investment in data collection. Our research is right in the forefront of ICT research, leading the international effort of extending database technologies to support data management and query processing for very large and highly complex data.Read moreRead less