Bayesian inference for complex regression models using mixtures. The project will use mixtures to flexibly model complex regression functions and will develop Bayesian methods for carrying out statistical inference on these models. The models will deal with both Gaussian and non-Gaussian data. Multiple explanatory variables are dealt with by mixing simple additives to produce flexible high dimensional function estimates. Variable selection and model averaging will be used to identify important v ....Bayesian inference for complex regression models using mixtures. The project will use mixtures to flexibly model complex regression functions and will develop Bayesian methods for carrying out statistical inference on these models. The models will deal with both Gaussian and non-Gaussian data. Multiple explanatory variables are dealt with by mixing simple additives to produce flexible high dimensional function estimates. Variable selection and model averaging will be used to identify important variables and thus make the estimation more efficient. The methods will be extended to multivariate responses where account will taken be taken of the structure of the dependence between responses.Read moreRead less
Synchrotrons, wavelet analysis and novel imaging techniques - applying physics tools to the war against breast cancer. Breast cancer leads to the second highest number of person-years of life lost due to cancer in Australia, with little known about its transport around the body. Current screening methods for breast cancer are neither 100% sensitive or specific and are heavily dependent upon expert training. This project will contribute by yielding valuable information on the transport of breast ....Synchrotrons, wavelet analysis and novel imaging techniques - applying physics tools to the war against breast cancer. Breast cancer leads to the second highest number of person-years of life lost due to cancer in Australia, with little known about its transport around the body. Current screening methods for breast cancer are neither 100% sensitive or specific and are heavily dependent upon expert training. This project will contribute by yielding valuable information on the transport of breast cancer and contribute to the development of an automated diagnostic method, with the possibility of its application to other diseases. The project will also involve members of the regional community, train regional scientists and provide synchrotron experience for Australian scientists in time for Australia's first synchrotron.Read moreRead less
Nonlinear Dynamics of Pulse Coupled Oscillators. A mathematical model of the heart pacemaker system will be created, based on simple interacting units. These units have been shown to be good models of physiological information e.g. the discrimination of different influences on heart rate. We will firstly look at the interaction of the units in simple combinations and then tune the model to mimic the behaviour of the cardiac pacemaker.
Potential benefits may arise from elucidating the mechanis ....Nonlinear Dynamics of Pulse Coupled Oscillators. A mathematical model of the heart pacemaker system will be created, based on simple interacting units. These units have been shown to be good models of physiological information e.g. the discrimination of different influences on heart rate. We will firstly look at the interaction of the units in simple combinations and then tune the model to mimic the behaviour of the cardiac pacemaker.
Potential benefits may arise from elucidating the mechanisms underlying arrhythmias which contribute to ?sudden cardiac death? in young men, and suggesting strategies for artificial pacemakers to effectively arrest abnormal rhythms before they convert to potentially fatal fibrillation.Read moreRead less
Model Update with Localisation, Constraints and Abstraction. This project will fundamentally provide a new paradigm and a system prototype for advanced computer aided system modification. It will significantly enhance Australia's leading role in the cutting edge research in computer aided system development. By applying the new methodology and technology, Australian IT industry will significantly improve its capacity for developing highly complex hardware and software systems for various applica ....Model Update with Localisation, Constraints and Abstraction. This project will fundamentally provide a new paradigm and a system prototype for advanced computer aided system modification. It will significantly enhance Australia's leading role in the cutting edge research in computer aided system development. By applying the new methodology and technology, Australian IT industry will significantly improve its capacity for developing highly complex hardware and software systems for various applications. With a strong research program across different areas such as knowledge system update, model checking and software development, and a collaborative research training environment, this project will strengthen Australia's international reputation as a leader in computing and IT research.Read moreRead less
Developing Sophisticated e-Business Automation. This project will provide theoretical foundations and a practical platform for developing advanced e-business automation technology. As such, it will significantly enhance Australia's leading role in the cutting edge research on e-business automation. By applying the new methodology and technology, Australian IT industries will be able to develop highly efficient e-market application systems, which will be financially beneficial to most organizatio ....Developing Sophisticated e-Business Automation. This project will provide theoretical foundations and a practical platform for developing advanced e-business automation technology. As such, it will significantly enhance Australia's leading role in the cutting edge research on e-business automation. By applying the new methodology and technology, Australian IT industries will be able to develop highly efficient e-market application systems, which will be financially beneficial to most organizations as Australia business and institutions are moving towards a more electronically oriented future. With a strong research team and collaborative research training environment, this project will further promote Australia's international reputation as a leader in Computing and IT research.Read moreRead less
Asynchronous Continuous Time Conditioning. Methodology for reasoning about Asynchronous Temporal Conditional Events (ATCE) obtains, complete with logical calculus for causal relations, reasoning about continuous time belief change, and markov chain algorithms calculating joint distributions of ATCE's.
Current techniques, including bayesian nets, are oblivious to temporal aspects; within our model they can be enhanced to recognize dynamic time changes. Ours is the first such unified model and ....Asynchronous Continuous Time Conditioning. Methodology for reasoning about Asynchronous Temporal Conditional Events (ATCE) obtains, complete with logical calculus for causal relations, reasoning about continuous time belief change, and markov chain algorithms calculating joint distributions of ATCE's.
Current techniques, including bayesian nets, are oblivious to temporal aspects; within our model they can be enhanced to recognize dynamic time changes. Ours is the first such unified model and first to link conditional objects with continuous time constraints.
Need for structures we propose arises in diagnostic reasoning, bayesian learning, temporal databases, and time-dependent data mining. Several commercial products (like Microsoft Office Assistant)could apply them forthwith.Read moreRead less
Fundamental Studies in System Identification. To operate a dynamic system such as a chemical process plant or an economy one needs two things; the equations describing the system; a way of regulating the system to provide desired outcomes. System identification provides the first; control engineering design provides the second. This proposal addresses three important problems in system identification and control. Firstly since the equations can never be known precisely we aim to determine what i ....Fundamental Studies in System Identification. To operate a dynamic system such as a chemical process plant or an economy one needs two things; the equations describing the system; a way of regulating the system to provide desired outcomes. System identification provides the first; control engineering design provides the second. This proposal addresses three important problems in system identification and control. Firstly since the equations can never be known precisely we aim to determine what is the best one can do? Secondly to provide then tight error bounds for the control design;
thirdly to develop new methods for some hitherto unresolved problems in system identification.Read moreRead less
Joint System Identification for Point Processes and Time-series. In various application areas such as neurophysiology, earthquake modeling, price spikes in electricity markets, the data of interest are point processes (aka sequences of events) or combinations of point processes and analog signals. To understand the underlying subject of interest we need to be able to extract the maximum information from these observation sequences. The current tools for doing this are very limited. This resear ....Joint System Identification for Point Processes and Time-series. In various application areas such as neurophysiology, earthquake modeling, price spikes in electricity markets, the data of interest are point processes (aka sequences of events) or combinations of point processes and analog signals. To understand the underlying subject of interest we need to be able to extract the maximum information from these observation sequences. The current tools for doing this are very limited. This research program will develop the complex signal processing and system methodology needed to create a suitable tool set.Read moreRead less
Feedback Architectures with Parallel Communication Channels. Feedback control is an enabling, though often hidden, technology. For example, without control loops, cars, mining and manufacturing plants cannot operate in an efficient and safe manner. To reduce costs, there has been a trend to use general purpose communication systems, such as WiFi, for feedback control. These communication systems have only limited capacity and reliability. This can lead to performance degradation and system failu ....Feedback Architectures with Parallel Communication Channels. Feedback control is an enabling, though often hidden, technology. For example, without control loops, cars, mining and manufacturing plants cannot operate in an efficient and safe manner. To reduce costs, there has been a trend to use general purpose communication systems, such as WiFi, for feedback control. These communication systems have only limited capacity and reliability. This can lead to performance degradation and system failure. The current project aims at proposing novel robust networked control system architectures. Our results will be useful to allow industries to use standard communications technology for control, thus, alleviating costs associated with developing dedicated application specific communication infrastructure.Read moreRead less
Continued Fractions and Torsion on Hyperelliptic Curves. Scientific advance should not blindly add to our knowledge; a true advance brings insights that collapse different issues into one. Understanding more is to need to remember less. For an important class of examples, this project identifies the study of a fundamental invariant of a quadratic number field, its regulator and hence its class number, with maximum torsion on the Jacobian variety of an hyperelliptic curve. The investigator's meth ....Continued Fractions and Torsion on Hyperelliptic Curves. Scientific advance should not blindly add to our knowledge; a true advance brings insights that collapse different issues into one. Understanding more is to need to remember less. For an important class of examples, this project identifies the study of a fundamental invariant of a quadratic number field, its regulator and hence its class number, with maximum torsion on the Jacobian variety of an hyperelliptic curve. The investigator's methods will surprise some longstanding problems into submission and in particular will lead them to reveal full data on torsion on hyperelliptic curves of low genus.
Read moreRead less