From Universal Induction to Intelligent Systems. The dream of creating artificial devices that (out)reach human intelligence is an old one. What makes this challenge so interesting? A solution would have enormous implications for our society, and there are arguments that the AI problem might be solved within a couple of decades. Specialized intelligent systems are actually already pervasive (finger print, handwriting, speech, and face recognition; spam filtering; search engines; computer chess; ....From Universal Induction to Intelligent Systems. The dream of creating artificial devices that (out)reach human intelligence is an old one. What makes this challenge so interesting? A solution would have enormous implications for our society, and there are arguments that the AI problem might be solved within a couple of decades. Specialized intelligent systems are actually already pervasive (finger print, handwriting, speech, and face recognition; spam filtering; search engines; computer chess; robots). This decade the first presumably complete mathematical theory of AI has been proposed. By working out this theory, this project will significantly contribute to the foundations of inductive inference and AI, and ultimately lead to smarter software and intelligent systems.Read moreRead less
Location-Based Personalisation in Mobile Commerce (M-Commerce). M-commerce, though playing an important role in future competitiveness of Australia, suffers a low user demand. While location-based services have taken off in Europe, they are still at their infancy in Australia. In terms of IT access, Australia is ranked lower than many Asian countries. Our work gains an understanding of users' concerns and expectations of location-based services, which leads to better application designs and thus ....Location-Based Personalisation in Mobile Commerce (M-Commerce). M-commerce, though playing an important role in future competitiveness of Australia, suffers a low user demand. While location-based services have taken off in Europe, they are still at their infancy in Australia. In terms of IT access, Australia is ranked lower than many Asian countries. Our work gains an understanding of users' concerns and expectations of location-based services, which leads to better application designs and thus a wider adoption. An examination of users' attitude towards personalised content and concerns about data privacy provides insights to Australian legislation in relation to telemarketing and data-driven marketing. National benefits will stem from a balance between telemarketing efficiency and users' benefits.Read moreRead less
Developing Reliable Bio-Crypto Features for Mobile Template Protection. Cost of identity theft crimes were at multi-million dollars in Australia in 2007. Technically this is due to the fact that conventional personal identification number and token based security mechanisms cannot identify genuine users. Biometric fingerprint security systems emerge as a promising solution. However protection of the mobile embedded fingerprint template itself is an unresolved problem. The project aims to devel ....Developing Reliable Bio-Crypto Features for Mobile Template Protection. Cost of identity theft crimes were at multi-million dollars in Australia in 2007. Technically this is due to the fact that conventional personal identification number and token based security mechanisms cannot identify genuine users. Biometric fingerprint security systems emerge as a promising solution. However protection of the mobile embedded fingerprint template itself is an unresolved problem. The project aims to develop new ways designing bio-cryptosystems that provide strong security strength. The project will bring new body of knowledge into this field and place Australia in the forefront of this research, and also result in strengthened security of IT infrastructure and systems for industries.Read moreRead less
Adaptive data stream processing in heterogeneous distributed computing environments using real-time context. This project falls within the ARC research priority goal, Smart Information Use. The innovative contributions of this project through the development of adaptive data stream mining algorithms for heterogeneous devices will have an impact on a range of emerging application areas such as:
1. Meeting time-critical, intelligent information needs of the mobile workforce (e.g. mobile healthca ....Adaptive data stream processing in heterogeneous distributed computing environments using real-time context. This project falls within the ARC research priority goal, Smart Information Use. The innovative contributions of this project through the development of adaptive data stream mining algorithms for heterogeneous devices will have an impact on a range of emerging application areas such as:
1. Meeting time-critical, intelligent information needs of the mobile workforce (e.g. mobile healthcare professionals, stockbrokers). 2. Improving Intelligent Transportation Systems via in-vehicle analysis and crash prevention. 3. Facilitating 'on-board' analysis in sensors that monitor the environment and patients. The project will enhance Australia's leading international role in the area of data stream processing in distributed computing environments.Read moreRead less
Added depth: automated high level image interpretation. Humans are very good at understanding the world through imagery, but computers lack this fundamental capacity because they lack experience of what they might see. This project will provide this experience by combining the large volumes of imagery on the Internet with three dimensional information generated by humans for other purposes.
Hybrid optimisation for automatic large-scale video annotation. Optimization is the basis for solving many problems in Computer Vision, such as three-dimensional geometry recovery, image segmentation, scene labeling and object recognition. This project will develop new optimisation techniques and demonstrate their suitability for large-scale video annotation, which is key to visual data mining and scene understanding.
Robust Preference Inference from Spatial-Temporal Interaction Networks. This project aims to develop innovative techniques for effectively and efficiently managing user preference profiles from less labelled, sparse and noisy interaction data. A unified novel learning framework along with a set of data analysis techniques are expected to be developed from this project, which will provide a non-intrusive way of conducting predictive analysis on user preference profiling via discovering human expl ....Robust Preference Inference from Spatial-Temporal Interaction Networks. This project aims to develop innovative techniques for effectively and efficiently managing user preference profiles from less labelled, sparse and noisy interaction data. A unified novel learning framework along with a set of data analysis techniques are expected to be developed from this project, which will provide a non-intrusive way of conducting predictive analysis on user preference profiling via discovering human explicit and implicit interest domains. The expected results of this application will not only maintain Australia's leadership in this frontier research area, but also support many important applications that safeguard Australian people and economy such as cyber security, healthcare, and e-Commerce.Read moreRead less
Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection. The last two decades have seen an escalating interest in automating the coding of facial expressions. Despite this keen interest, the promise of computer vision systems to accurately code facial expressions in natural circumstances remains elusive. Our interdisciplinary team will research a new paradigm to account for facial alignment distortion directly rather than ai ....Solve it or Ignore it? The Challenge of Alignment Distortion and Creating Next Generation Automatic Facial Expression Detection. The last two decades have seen an escalating interest in automating the coding of facial expressions. Despite this keen interest, the promise of computer vision systems to accurately code facial expressions in natural circumstances remains elusive. Our interdisciplinary team will research a new paradigm to account for facial alignment distortion directly rather than aiming to achieve invariance to it. The project will also research new data agnostic feature compaction capabilities to enable scalable learning on the world’s largest and challenging expression dataset available to us through international collaboration. Tackling these two major open problems will make accurate coding of facial expressions in natural environments achievable.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
On effectively modelling and efficiently discovering communities from large networks. Finding and maintaining close communities from very large scale, dynamically changing networks is interesting and challenging. This project aims to develop new techniques to identify such communities as fast as possible through exploiting the rich semantics and individual relationships within the communities.