Concept-Based Multilingual Web Content Mining. Towards smart use of Web information, this pioneer project will develop an innovative concept-based approach for discovering global knowledge embedded within multilingual Web documents. Departing from the traditional bilingual term-to-term machine translation techniques, the approach overcomes the notorious vocabulary mismatch problem by enabling synchronised lexical mapping of multiple languages. A series of intelligent concept-based techniques usi ....Concept-Based Multilingual Web Content Mining. Towards smart use of Web information, this pioneer project will develop an innovative concept-based approach for discovering global knowledge embedded within multilingual Web documents. Departing from the traditional bilingual term-to-term machine translation techniques, the approach overcomes the notorious vocabulary mismatch problem by enabling synchronised lexical mapping of multiple languages. A series of intelligent concept-based techniques using fuzzy logic and neural networks will be investigated to support smart Web information browsing and exploration. This project will provide valuable new insights into developing state-of-the-art multilingual Web mining applications for enhancing business intelligence in Australia's knowledge driven industries.Read moreRead less
Efficient data manipulation in document classification. Document Classification has an enormous relevance in an era where large amounts of textual information is available. Document Classification is based on statistical and machine learning techniques that model documents represented as points in a multidimensional space. The Computer Engineering Laboratory (CEL) has ongoing projects using neural networks and other techniques for document classification. We are developing a development environm ....Efficient data manipulation in document classification. Document Classification has an enormous relevance in an era where large amounts of textual information is available. Document Classification is based on statistical and machine learning techniques that model documents represented as points in a multidimensional space. The Computer Engineering Laboratory (CEL) has ongoing projects using neural networks and other techniques for document classification. We are developing a development environment for large classification tasks, and Prof. Lee¡¯s work will focus in managing large amounts of data for them. Using his experience in data compression, databases and web applications, he will produce a set of tools for handling Gigabytes of textual data in our classification environment.Read moreRead less
Semantic Authentication of Visual Data. Data authentication systems can detect the smallest modification to a message. Authentication systems for media objects such as images, and audio and video clips have a different requirement they must ensure authenticity of the content without needing all the changes to be detectable. The aims of this project are to develop a framework for design and analysis of image and video authentication systems, and construct secure and flexible systems that can be ....Semantic Authentication of Visual Data. Data authentication systems can detect the smallest modification to a message. Authentication systems for media objects such as images, and audio and video clips have a different requirement they must ensure authenticity of the content without needing all the changes to be detectable. The aims of this project are to develop a framework for design and analysis of image and video authentication systems, and construct secure and flexible systems that can be used in practice. This research addresses the urgent need of providing security for multimedia objects in electronic commerce and is of high importance to the acceptance of advanced communication and information services.Read moreRead less
Extensions to the page scoring algorithm in internet search engine studies. This project proposes to study two extensions to the Page rank equation which is one of the theoretical underpinning of Google's web page scoring engine. In particular, we wish to explore ways to combine page connectivity and page characteristics in the scoring of web pages. This will be the first time a rational way is proposed for combining these two factors. The expected outcome will be a deeper understanding on how t ....Extensions to the page scoring algorithm in internet search engine studies. This project proposes to study two extensions to the Page rank equation which is one of the theoretical underpinning of Google's web page scoring engine. In particular, we wish to explore ways to combine page connectivity and page characteristics in the scoring of web pages. This will be the first time a rational way is proposed for combining these two factors. The expected outcome will be a deeper understanding on how these two factors affect the scores of a web page in a search engine, and hence how they affect the visibility of the page in response to a query.
Read moreRead less
Data structures which change with time, a machine learning approach. Visibility of web pages, based on page importance, on the Internet controls their accessibility by users which is critical for e-Commerce applications. The page importance depends on its contents and its link structure to other web pages, both of which can be time varying. This project proposes a novel model in which time varying aspects of the changes to contents and their link structures are captured, thus allowing us a bette ....Data structures which change with time, a machine learning approach. Visibility of web pages, based on page importance, on the Internet controls their accessibility by users which is critical for e-Commerce applications. The page importance depends on its contents and its link structure to other web pages, both of which can be time varying. This project proposes a novel model in which time varying aspects of the changes to contents and their link structures are captured, thus allowing us a better understanding of how these influence the page importance over time. It will also allow us insight on how to improve the visibility of web pages.Read moreRead less
Investigations in Learning Algorithms for Web Page Scoring Systems. Modification of web page scores to satisfy requirements, e.g., one page should have a higher page score than another, a home page should have higher score than any other pages in the same site, using modifications of the forcing function, and the link connectivity matrix respectively of the PageRank equation will be studied. By clustering web pages either by ranks or by scores will help overcome issues of scale and complexity wh ....Investigations in Learning Algorithms for Web Page Scoring Systems. Modification of web page scores to satisfy requirements, e.g., one page should have a higher page score than another, a home page should have higher score than any other pages in the same site, using modifications of the forcing function, and the link connectivity matrix respectively of the PageRank equation will be studied. By clustering web pages either by ranks or by scores will help overcome issues of scale and complexity which are required for the live world wide web. Outcomes will provide a rational basis together with practical methods for modifying web page scores by a web site administrator.Read moreRead less
Investigations into Distributed Information Processing of the World Wide Web: Addressing Major Bottlenecks in Search Engine Design. The Internet is a global medium used increasingly for commercial purposes. Nationally provided commercial services and products, as well as general types of information are made available globally via the Internet. Web search engines are the only method by which a common user can find a relevant service or information on the Internet. The sheer size and the dynamics ....Investigations into Distributed Information Processing of the World Wide Web: Addressing Major Bottlenecks in Search Engine Design. The Internet is a global medium used increasingly for commercial purposes. Nationally provided commercial services and products, as well as general types of information are made available globally via the Internet. Web search engines are the only method by which a common user can find a relevant service or information on the Internet. The sheer size and the dynamics of the Internet pose a significant challenge to search engines. This project proposes to address some major bottlenecks in search engine design (viz. the page rank computation). This may help future search engines to maintain a good level of Web penetration and, consequently will help to ensure a suitable coverage of nationally available services and information to the world.
Read moreRead less
Robust feature extraction for automatic speech recognition. Speech is perhaps the most natural and efficient mode of communication for humans. Therefore, it has always been a dream for many people to communicate with machines via speech. Significant advances have been made in the last five decades in the area of automatic speech recognition. Though the currently available speech recognisers work reasonably well in noise-free office environments, their performance deteriorates drastically when th ....Robust feature extraction for automatic speech recognition. Speech is perhaps the most natural and efficient mode of communication for humans. Therefore, it has always been a dream for many people to communicate with machines via speech. Significant advances have been made in the last five decades in the area of automatic speech recognition. Though the currently available speech recognisers work reasonably well in noise-free office environments, their performance deteriorates drastically when they are deployed in real-life situations due to the presence of background noise and other distortions. The problem of robust speech recognition will be researched in this project. Read moreRead less
Agent-based coordination and negotiation technologies for decentralised service workflow management. This project will enhance the nation's expertise in ICT in general and smart information use in particular. In the real world, process management is a key issue in any workplace organisation which needs to be supported by workflow systems, particularly in this Internet and Web services era. This project will develop an innovative framework and the corresponding technologies for service workflow m ....Agent-based coordination and negotiation technologies for decentralised service workflow management. This project will enhance the nation's expertise in ICT in general and smart information use in particular. In the real world, process management is a key issue in any workplace organisation which needs to be supported by workflow systems, particularly in this Internet and Web services era. This project will develop an innovative framework and the corresponding technologies for service workflow management. The research will assist many organisations to effectively develop and deliver more efficient, reliable, flexible and adaptive business applications. Consequently, this will enhance the ability of many Australian organisations to run more productively and more competitively.Read moreRead less
Frequency-related features derived from phase spectrum for robust speech recognition. Though the currently available speech recognizers work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. In order to overcome this problem, new frequency-related features are proposed in this project for speech recognition. These features are derived from the phase spectrum of the speech signal, and are expected to be robust t ....Frequency-related features derived from phase spectrum for robust speech recognition. Though the currently available speech recognizers work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. In order to overcome this problem, new frequency-related features are proposed in this project for speech recognition. These features are derived from the phase spectrum of the speech signal, and are expected to be robust to the additive noise distortion. These features will make the speech recognizer less sensitive to noise and will enhance its utility in a number of applications in the telecommunication and business world.Read moreRead less