Towards knowledge discovery from imperfect and evolving data. Information extraction from data is critical, both to analyse and protect consumer data. However, many learning techniques are developed using perfect, static datasets, quite different to messy, ever-changing real-world data. This project aims to develop data analytics techniques that can extract accurate information in complex structures from imperfect/incomplete data that changes over time. Expected outcomes are a prototype tool, te ....Towards knowledge discovery from imperfect and evolving data. Information extraction from data is critical, both to analyse and protect consumer data. However, many learning techniques are developed using perfect, static datasets, quite different to messy, ever-changing real-world data. This project aims to develop data analytics techniques that can extract accurate information in complex structures from imperfect/incomplete data that changes over time. Expected outcomes are a prototype tool, tested on real datasets, that combines new techniques in data modelling, algorithm development, and system design. Likely benefits are enhanced Australia's competence in data science through student training and new, robust data tools relevant to critical sectors such as cybersecurity, healthcare, and defence.Read moreRead less
Privacy preserving data sharing in data mining environments. Preserving privacy in data mining among various enterprises and organisations is essential for many real world applications in areas like health surveillance, business analysis, fraud detection and terror protection. Efficient and effective techniques are badly needed to protect privacy in data sharing and data mining. The developed cutting-edge techniques in this project will be implemented in freely available open source software too ....Privacy preserving data sharing in data mining environments. Preserving privacy in data mining among various enterprises and organisations is essential for many real world applications in areas like health surveillance, business analysis, fraud detection and terror protection. Efficient and effective techniques are badly needed to protect privacy in data sharing and data mining. The developed cutting-edge techniques in this project will be implemented in freely available open source software tools, empowering Australian organisations to utilise the techniques to develop intelligent systems in data sharing environments. These techniques will ultimately lead to better utilisation of the information available in many enterprises and organisations.Read moreRead less
Effective and accurate model dynamics, deterministic and stochastic, across multiple space and time scales. A persistent feature of complex systems in engineering and science is the emergence of macroscopic, coarse grained, coherent behaviour from the interactions of microscopic agents (molecules, cells, grains) and with their environment. In current modeling, ranging from ecology to materials science, the underlying microscopic mechanisms are often known, but the closures to translate microscal ....Effective and accurate model dynamics, deterministic and stochastic, across multiple space and time scales. A persistent feature of complex systems in engineering and science is the emergence of macroscopic, coarse grained, coherent behaviour from the interactions of microscopic agents (molecules, cells, grains) and with their environment. In current modeling, ranging from ecology to materials science, the underlying microscopic mechanisms are often known, but the closures to translate microscale knowledge to a system level macroscopic description are rarely available in closed form. Our novel methodology will explore this stumbling block, and promises to radically change the modeling, exploration and understanding of multiscale complex system behaviour.Read moreRead less
Modelling of multiscale systems in engineering and science supports large-scale equation-free simulations and analysis. A persistent feature of complex systems in engineering and science is the emergence of macroscopic, coarse grained, coherent behaviour from the interactions of microscopic agents (molecules, cells) and with their environment. In current modeling, ranging from ecology to materials science, the underlying microscopic mechanisms are known, but the closures to translate microscale ....Modelling of multiscale systems in engineering and science supports large-scale equation-free simulations and analysis. A persistent feature of complex systems in engineering and science is the emergence of macroscopic, coarse grained, coherent behaviour from the interactions of microscopic agents (molecules, cells) and with their environment. In current modeling, ranging from ecology to materials science, the underlying microscopic mechanisms are known, but the closures to translate microscale knowledge to a system level macroscopic description are rarely available in closed form. Our novel, equation free, computational methodologies will circumvent this stumbling block, and promises to radically change the modeling, exploration and understanding of complex system behavior. We continue to develop this powerful computational methodology. Read moreRead less
A process model of visual working memory. This project aims to develop a process model of encoding of items into memory. Working memory is central to almost all cognitive functions, but little is known about short-term memory for visual information. Progress in this area is slow because of a focus on models that do not specify the processes underlying memory, and no model explains the processes that would limit the number of items the memory can hold to four. A process model is expected to addre ....A process model of visual working memory. This project aims to develop a process model of encoding of items into memory. Working memory is central to almost all cognitive functions, but little is known about short-term memory for visual information. Progress in this area is slow because of a focus on models that do not specify the processes underlying memory, and no model explains the processes that would limit the number of items the memory can hold to four. A process model is expected to address fundamental issues in visual working memory.Read moreRead less
Learning human activities through low cost, unobtrusive RFID technology. A rapidly growing aged population presents many challenges to Australia's health and aged care services. The outcomes of this project will help aging Australians live in their own homes longer, with greater independence and safety by providing an automated, unobtrusive means for health professionals to monitor activity and intervene as required.
Is New Guinea the missing link for understanding Australia’s rainforests? This project aims to understand the extent to which the animals in Australia have shared histories with animals from the islands of Melanesia, and especially New Guinea. Key outcomes will be identification of hotspots of unique and high evolutionary diversity across both regions, and understanding of whether New Guinea has been an overall refuge or source for rainforest animals as Australia became more arid over the last 2 ....Is New Guinea the missing link for understanding Australia’s rainforests? This project aims to understand the extent to which the animals in Australia have shared histories with animals from the islands of Melanesia, and especially New Guinea. Key outcomes will be identification of hotspots of unique and high evolutionary diversity across both regions, and understanding of whether New Guinea has been an overall refuge or source for rainforest animals as Australia became more arid over the last 20 million years. Expected benefits include addressing fundamental gaps in our knowledge of the history of both the Australian continent and its resident biota such as when landbridges first formed with New Guinea, and the identification of priority areas for conservation investment in both Australian and Melanesia.Read moreRead less
The fundamental equations for inversion of operator pencils. This project seeks to deepen understanding of how complex systems may be significantly changed by incremental changes to ambient conditions. Mathematical models of complex systems (climate change processes, optimal driving strategies, efficient distribution policies, effective search routines) often depend on key parameters. If small perturbations to the parameters cause large changes to the solution, then the perturbations are said to ....The fundamental equations for inversion of operator pencils. This project seeks to deepen understanding of how complex systems may be significantly changed by incremental changes to ambient conditions. Mathematical models of complex systems (climate change processes, optimal driving strategies, efficient distribution policies, effective search routines) often depend on key parameters. If small perturbations to the parameters cause large changes to the solution, then the perturbations are said to be singular. This project aims to reveal the underlying mathematical structures and develop new computational algorithms to analyse a general class of perturbed systems both locally near an isolated singularity and globally. It plans to use these algorithms to solve systems of equations, calculate generalised inverse operators, examine perturbed Markov processes, and estimate exit times from meta-stable states in stochastic population dynamics.Read moreRead less
Single and dual process models of recognition memory: Reconciliation of behavioural, electrophysiological, and neuroimaging data. Advanced brain scanning technologies are increasingly used to study human memory. As well as being important for our basic understanding of memory, they also tell us how memory is affected by normal development, ageing, disease, and injury. Unfortunately, because these technologies are so new, a gap has opened up between our psychological understanding of memory and t ....Single and dual process models of recognition memory: Reconciliation of behavioural, electrophysiological, and neuroimaging data. Advanced brain scanning technologies are increasingly used to study human memory. As well as being important for our basic understanding of memory, they also tell us how memory is affected by normal development, ageing, disease, and injury. Unfortunately, because these technologies are so new, a gap has opened up between our psychological understanding of memory and the physiological events measured by the scanning technologies. This has created a problem for how we should interpret the results that are found. The present project aims to close this gap by applying new research methodologies and theoretical insights based on our previous research.Read moreRead less
Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features t ....Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features to analyse in each modality and the hidden relationships between them. The use of deep belief networks has produced promising results in several fields, such as speech recognition, and so this project believes that our approach has the potential to improve both the sensitivity and specificity of breast cancer detection.Read moreRead less