Developing Minimum Message Length and Support Vector Machine methods to predict user behaviour. Predicting and modelling customer behaviour enables considerable savings in the telecommunications industry and elsewhere. The resulting predictive models facilitate identifying novice users, identifying fraud, responding to users' needs, guiding and advising users, and forwarding useful information.
We consider two cutting-edge data mining approaches, Minimum Message Length (developed and led by ....Developing Minimum Message Length and Support Vector Machine methods to predict user behaviour. Predicting and modelling customer behaviour enables considerable savings in the telecommunications industry and elsewhere. The resulting predictive models facilitate identifying novice users, identifying fraud, responding to users' needs, guiding and advising users, and forwarding useful information.
We consider two cutting-edge data mining approaches, Minimum Message Length (developed and led by Monash) and Support Vector Machines, in order to create efficient tailor-made software.
Our software will respond to specific groups of users, and their changes over time, rather than just the average user. Moreover, it will integrate the functionalities of existing individual data mining software.Read moreRead less
Managing quality of experience delivery in new generation telecommunications networks with e-negotiation. New generation telecommunications networks are required to support increasingly demanding services, including interactive multimedia and conferencing. The success of these networks will rely on the users' perception of their quality of experience. The management of these networks will rely on the ability of informed decision making that competes effectively for limited resources in such a ....Managing quality of experience delivery in new generation telecommunications networks with e-negotiation. New generation telecommunications networks are required to support increasingly demanding services, including interactive multimedia and conferencing. The success of these networks will rely on the users' perception of their quality of experience. The management of these networks will rely on the ability of informed decision making that competes effectively for limited resources in such a highly dynamic environment. This project will design information distribution strategies and smart decision making agents that negotiate a user's quality of experience using market mechanisms. Designs from this project will be trialled and validated in the partner's commercial networks.Read moreRead less
Smart communications network management: Delivering bundled interdependent services across internetworked heterogeneous domains. Sophisticated communications network management (data, voice, video) is crucial to the global economy. The field is worth several billion dollars per annum. This project will generate expertise that addresses and solves an important problem in communications management, will enable Australia to use communications networks more effectively, and will advance communicatio ....Smart communications network management: Delivering bundled interdependent services across internetworked heterogeneous domains. Sophisticated communications network management (data, voice, video) is crucial to the global economy. The field is worth several billion dollars per annum. This project will generate expertise that addresses and solves an important problem in communications management, will enable Australia to use communications networks more effectively, and will advance communications technology. 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
Visual Solutions for Automated Translation Between Spoken and Signed Languages. We propose to build a robust visual speech recognition system that analyzes images of spoken language and achieves a recognition of the utterances with at least human expert recognition rates. This visual speech recognition system will then be integrated with our existing gesture recognition system to improve performance, just as humans combine visual and audio data for language understanding. The result will be a sy ....Visual Solutions for Automated Translation Between Spoken and Signed Languages. We propose to build a robust visual speech recognition system that analyzes images of spoken language and achieves a recognition of the utterances with at least human expert recognition rates. This visual speech recognition system will then be integrated with our existing gesture recognition system to improve performance, just as humans combine visual and audio data for language understanding. The result will be a system providing translation between English and the Australian sign language Auslan in a practical application domain. Significantly, our work will provide insights into the cognitive models of neural activity linking language and gesture.Read moreRead less
Automated Vector Extraction from Airborne Laser Scan Data. This project considers the problem of automatically extracting and vectorising the outlines of objects from Airborne Laser Scanning (ALS) data. The industry partner, AAM GeoScan, is a leading user of ALS systems in Australia, and has a need to develop automated solutions to this problem. ALS data is typically a dense cloud of 3D point data which represents the local terrain, as well as any trees, buildings or vehicles which may be in t ....Automated Vector Extraction from Airborne Laser Scan Data. This project considers the problem of automatically extracting and vectorising the outlines of objects from Airborne Laser Scanning (ALS) data. The industry partner, AAM GeoScan, is a leading user of ALS systems in Australia, and has a need to develop automated solutions to this problem. ALS data is typically a dense cloud of 3D point data which represents the local terrain, as well as any trees, buildings or vehicles which may be in the field of view. Spatial data is a very important resource, widely used in many types of urban and rural planning operations. Planning software packages require vectorised descriptions of building outlines and other spatial data, however this is not presently available from raw ALS data. The project will investigate this problem and develop new and effective means for producing it automatically from raw ALS data. Expected outcomes include a successful research masters studentship, the development of novel solutions to the problem which are directly applicable to the industry partner's core business, peer reviewed publications, and an strengthened link between the universities and the industry partner.Read moreRead less
High Performance Firewalls for Network Security. This project aims to improve the accuracy and efficiency of firewall systems for defending the security of large networks. The role of a network firewall is to detect and block unauthorised network traffic. Our industry partner, IntelliGuard, is developing a parallel system architecture for firewalls, which will provide sufficient processing capacity to support more sophisticated traffic analysis in high speed networks. Our aim is to develop paral ....High Performance Firewalls for Network Security. This project aims to improve the accuracy and efficiency of firewall systems for defending the security of large networks. The role of a network firewall is to detect and block unauthorised network traffic. Our industry partner, IntelliGuard, is developing a parallel system architecture for firewalls, which will provide sufficient processing capacity to support more sophisticated traffic analysis in high speed networks. Our aim is to develop parallel algorithms for traffic analysis and load balancing that can exploit the capacity of these new firewalls. This project provides an excellent opportunity for an Australian company to compete in the growing security market.Read moreRead less
Defending Against Attacks on Internet-Based Telephone Services (Voice Over IP). The telephone network is a critical platform for communication, used by all levels of society - government, the private sector and the general public. The shift to telephone services based on voice-over-IP technology holds the promise of significantly reducing costs for communication services. However, the Internet has long been plagued by a variety of network attacks. Reports of denial-of-service attacks, viruses an ....Defending Against Attacks on Internet-Based Telephone Services (Voice Over IP). The telephone network is a critical platform for communication, used by all levels of society - government, the private sector and the general public. The shift to telephone services based on voice-over-IP technology holds the promise of significantly reducing costs for communication services. However, the Internet has long been plagued by a variety of network attacks. Reports of denial-of-service attacks, viruses and break-in attempts frequently appear in the world news. A major impediment to confidence in voice-over-IP services is the risk of attacks on its infrastructure, and the potential for using weaknesses in voice-over-IP infrastructure to launch attacks on the existing telephone network.Read moreRead less
Bio-inspired speech analysis: Specialised information processing of vocalisations in the auditory brainstem. This project has the potential to benefit bionic ear and hearing aid users through the development of signal processing methods that mimic the amazing abilities of the brain. Speech perception performance by bionic ear users has reached a plateau and these new strategies could produce the breakthrough needed to provide the next increase in performance. The benefit for greater improved hea ....Bio-inspired speech analysis: Specialised information processing of vocalisations in the auditory brainstem. This project has the potential to benefit bionic ear and hearing aid users through the development of signal processing methods that mimic the amazing abilities of the brain. Speech perception performance by bionic ear users has reached a plateau and these new strategies could produce the breakthrough needed to provide the next increase in performance. The benefit for greater improved hearing has enormous benefit and potential for improving the quality of life of the hearing impaired, especially those with severe and profound hearing loss. In addition, the algorithms may provide more robust automatic speech recognition, making this technology more useful in everyday situations; the markets that this would open up are enormous.Read moreRead less
Robust next-generation detection techniques to defend operational networks against attacks. As networks are fast becoming one of the pillars of our society, network security is essential.
Without good security, networks will be unreliable, more costly, and restricted in the capabilities they can offer. The project will allow advanced anomaly and intrusion detection techniques to be used in the ultra-high speeds of the Internet core. It will provide the groundwork for the attack detection and p ....Robust next-generation detection techniques to defend operational networks against attacks. As networks are fast becoming one of the pillars of our society, network security is essential.
Without good security, networks will be unreliable, more costly, and restricted in the capabilities they can offer. The project will allow advanced anomaly and intrusion detection techniques to be used in the ultra-high speeds of the Internet core. It will provide the groundwork for the attack detection and prevention infrastructure of the future. Read moreRead less