New Developments for Bayesian statistical models and computational methods. Bayesian methods of statistical analysis provide a flexible theory for addressing inference in the presence of uncertainty. Consequently Bayesian methods have enabled scientific discovery in areas characterised as complex systems where new developments in modelling and computational methods have been crucial. Significant barriers to further success involve challenges in formulating and validating models, dealing with l ....New Developments for Bayesian statistical models and computational methods. Bayesian methods of statistical analysis provide a flexible theory for addressing inference in the presence of uncertainty. Consequently Bayesian methods have enabled scientific discovery in areas characterised as complex systems where new developments in modelling and computational methods have been crucial. Significant barriers to further success involve challenges in formulating and validating models, dealing with large data sets, and developing efficient computational methods. The principal aim of this project is to develop new Bayesian modelling and computational methodology which address these challenges with broad application.Read moreRead less
Design of a Reference Methodology for Extended Enterprise Architecture. Enterprises have nowadays a very critical perception of the actual benefits of Information Technology (IT). Significant investments in IT infrastructures have been made. However, in many cases no monetary benefits could be demonstrated. Enterprises Architectures provide a way to link the business and the IT perspective. This project aims to develop an operational methodology with a solid theoretical foundation for the design ....Design of a Reference Methodology for Extended Enterprise Architecture. Enterprises have nowadays a very critical perception of the actual benefits of Information Technology (IT). Significant investments in IT infrastructures have been made. However, in many cases no monetary benefits could be demonstrated. Enterprises Architectures provide a way to link the business and the IT perspective. This project aims to develop an operational methodology with a solid theoretical foundation for the design of such Enterprise Architectures. The outcomes and the innovation of this project are an extension of the popular Zachman Framework. Integrated modelling techniques proposed within the Architecture of Integrated Information Systems will be used to populate this framework.Read moreRead less
Design and Development of a Web-based Intelligent Multimedia Mining System. Increasing amounts of digital multimedia data in the form of video is being captured and stored. However, even the most advanced storage and retrieval techniques lack the features required to be used singly, or in combination, to fulfil a wide range of user needs and rapid access to multimedia resources, even in a very large video database. The core challenges are indeed to develop efficient, smart and intelligent web-ba ....Design and Development of a Web-based Intelligent Multimedia Mining System. Increasing amounts of digital multimedia data in the form of video is being captured and stored. However, even the most advanced storage and retrieval techniques lack the features required to be used singly, or in combination, to fulfil a wide range of user needs and rapid access to multimedia resources, even in a very large video database. The core challenges are indeed to develop efficient, smart and intelligent web-based multimedia mining in Australia and elsewhere. In this project, we will explore techniques and develop algorithms for content-based multimedia retrieval and mining in multimedia databases.Read moreRead less
Techniques to use stereo vision for improving person identification systems based on face recognition. The broad aim of this project is to use three-dimensional information available by processing images from stereo cameras in order to bridge the gap between constrained face recognition systems and viable systems that work well under varying illumination, changes in pose and variations in spectacles, facial hair and attire. Such a system will be useful in passenger verification at airports and a ....Techniques to use stereo vision for improving person identification systems based on face recognition. The broad aim of this project is to use three-dimensional information available by processing images from stereo cameras in order to bridge the gap between constrained face recognition systems and viable systems that work well under varying illumination, changes in pose and variations in spectacles, facial hair and attire. Such a system will be useful in passenger verification at airports and as a component of personal identification systems to counter terrorism. The key to successful face location and recognition is an effective combination of all data - range, luminance and colour - and techniques for this will be the discovered outcomes.Read moreRead less
Kernel methods for the analysis of whole bacterial genomes. This project addresses the fundamental scientific problem of the identification of regulatory regions and specific promoters within bacterial genomes, with a focus upon two organisms of great social, economic and bioterrism significance. From the machine learning perspective, the project will be the first to produce a kernel-based approach directly tailored to the problem of the detection of regulatory regions. The methods developed wil ....Kernel methods for the analysis of whole bacterial genomes. This project addresses the fundamental scientific problem of the identification of regulatory regions and specific promoters within bacterial genomes, with a focus upon two organisms of great social, economic and bioterrism significance. From the machine learning perspective, the project will be the first to produce a kernel-based approach directly tailored to the problem of the detection of regulatory regions. The methods developed will be made available through a straightforward web-based interface, allowing biologists throughout the world to utilize the approach as a tool to be applied to a progressively widening class of bacterial genomes, and even to eukaryotes. Read moreRead less
Ontologically-based Evaluation, Comparison and Engineering of Integrated Process Modelling Techniques. Integrated process modelling techniques such as UML and ARIS form the conceptual platform for many management and IT projects. Though most IS development tools contain these techniques, anecdotal evidence indicates many shortcomings. This project uses a well-established theory developed in philosophy and applied in information systems domains for the evaluation of these techniques. The expec ....Ontologically-based Evaluation, Comparison and Engineering of Integrated Process Modelling Techniques. Integrated process modelling techniques such as UML and ARIS form the conceptual platform for many management and IT projects. Though most IS development tools contain these techniques, anecdotal evidence indicates many shortcomings. This project uses a well-established theory developed in philosophy and applied in information systems domains for the evaluation of these techniques. The expected outcomes are evaluations of ARIS and UML. Thus, this project contributes to the development of two of the most popular modelling techniques. Based on the theory used and the results of an international empirical study, suggestions for the further development of these techniques will be derived.Read moreRead less
Audit Security Models for Multiparty Internet Transactions. The aim of this project is to conduct the study for a secure, low overhead means of auditing secure transactions between two parties over the Internet, especially where some doubt surrounds the trustfulness of the other party.
A study will be conducted in this project by investigating security models for multiparty secure transactions in order to identify a number of likely applications for the technology, to develop a high level arch ....Audit Security Models for Multiparty Internet Transactions. The aim of this project is to conduct the study for a secure, low overhead means of auditing secure transactions between two parties over the Internet, especially where some doubt surrounds the trustfulness of the other party.
A study will be conducted in this project by investigating security models for multiparty secure transactions in order to identify a number of likely applications for the technology, to develop a high level architecture of the solution.Read moreRead less
A toolkit of statistical methodology for a state-of-the-art software and decision support system for forest assessment using new airborne data. The aim is to develop statistical methods for efficient collection and interpretation of airborne laser data and videography, used to describe characteristics of the forest such as tree species, stand history and vertical distribution of foliage, and hence biodiversity and biomass. This is significant for meeting Australia's international and national en ....A toolkit of statistical methodology for a state-of-the-art software and decision support system for forest assessment using new airborne data. The aim is to develop statistical methods for efficient collection and interpretation of airborne laser data and videography, used to describe characteristics of the forest such as tree species, stand history and vertical distribution of foliage, and hence biodiversity and biomass. This is significant for meeting Australia's international and national environmental obligations, providing quality information to farmers and industry, and hence developing potential jobs in regional areas. Outcomes include a toolkit of statistical methods applicable to spatial modelling and analysis of very large datasets, a statistically valid software product, marketable estimation methods in carbon accounting, technology transfer, training, publications.Read moreRead less
Novel Applied Bayesian Statistics for Monitoring Neuromuscular Diseases. Neurological diseases such as motor neurone disease are caused by the progressive death of motor units serving a muscle. Currently there are no ways of quantifying and detecting change in the number of motor units serving a muscle which are non-invasive. Our research will provide an objective method for the progression of neuromuscular diseases to be monitored with minimal inconvenience to patients. This will allow clinic ....Novel Applied Bayesian Statistics for Monitoring Neuromuscular Diseases. Neurological diseases such as motor neurone disease are caused by the progressive death of motor units serving a muscle. Currently there are no ways of quantifying and detecting change in the number of motor units serving a muscle which are non-invasive. Our research will provide an objective method for the progression of neuromuscular diseases to be monitored with minimal inconvenience to patients. This will allow clinical trials for possible effective treatments of neurological diseases such as motor neurone disease to be conducted with an objective measurement of disease progression. Read moreRead less
Defending AI based FinTech Systems against Model Extraction Attacks. This project aims to develop new methods for defending artificial intelligence (AI) based FinTech systems from highly potent and insidious model extraction attacks whereby an adversary can steal the AI model from the system to cause intellectual property (IP) violation, business advantage disruption, and financial loss. This can be achieved by examining various attack models, creating active and utility-preserving defences, and ....Defending AI based FinTech Systems against Model Extraction Attacks. This project aims to develop new methods for defending artificial intelligence (AI) based FinTech systems from highly potent and insidious model extraction attacks whereby an adversary can steal the AI model from the system to cause intellectual property (IP) violation, business advantage disruption, and financial loss. This can be achieved by examining various attack models, creating active and utility-preserving defences, and inventing non-removable watermarks on AI models. The outcomes are new tools for securing AI-based FinTech systems before deployment and tools for IP violation forensics post-deployment. Such capabilities are beneficial by improving the security and safety of FinTech systems and other nationally critical AI systems.Read moreRead less