Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored ....Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored to individual characteristics. The success of this project could significantly advance the fundamental research in image analysis. Expected outcomes include new knowledge and algorithms for image analysis, which could benefit fields like biology and archaeology, where labeled images are hard to attain and scarce.Read moreRead less
Integrated Planning for Uncertainty-Centric Pilot Assistance Systems. This project aims to deliver a novel pilot assistance system to improve the viability, speed and safety of Helicopter Emergency Medical Services (HEMS) and Search and Rescue (SAR) missions. It will advance fundamental algorithms for probabilistic planning in partially observable scenarios to form the core technology of a pilot assistance system that accounts the various types of uncertainty faced by pilots in a typical HEMS/S ....Integrated Planning for Uncertainty-Centric Pilot Assistance Systems. This project aims to deliver a novel pilot assistance system to improve the viability, speed and safety of Helicopter Emergency Medical Services (HEMS) and Search and Rescue (SAR) missions. It will advance fundamental algorithms for probabilistic planning in partially observable scenarios to form the core technology of a pilot assistance system that accounts the various types of uncertainty faced by pilots in a typical HEMS/SAR missions. It will exploit recent advances in Partially Observable Markov Decision Processes (POMDPs) to recommend robust, safe, and pilot-aware mission and manoeuvring strategies to make HEMS/SAR operations safer for helicopter crews, and more effective for those in need of the service.Read moreRead less
DeepHoney: Automatic Honey Data Generation for Active Cyber Defence . This project aims to enhance the security of networks and information systems by empowering them with intelligent deception techniques to achieve proactive attack detection and defence. In recent times, the fictitious environment – honeypot designed by human experience becomes popular to attract attackers and capture their interactions. However, rules-based construction of honeypots fails in preserving the privacy, boosting th ....DeepHoney: Automatic Honey Data Generation for Active Cyber Defence . This project aims to enhance the security of networks and information systems by empowering them with intelligent deception techniques to achieve proactive attack detection and defence. In recent times, the fictitious environment – honeypot designed by human experience becomes popular to attract attackers and capture their interactions. However, rules-based construction of honeypots fails in preserving the privacy, boosting the attractiveness and evolving the system. The project expects to advance deep learning and yield novel DeepHoney technologies with associated publications and open-source software. This should benefit science, society, and the economy by building the next generation of active cyber defence systems. Read moreRead less
Democratisation of Deep Learning: Neural Architecture Search at Low Cost. The need to manually design Deep Learning-based Neural Networks (DNNs) limits their usage to AI experts and hinders the exploitation of their true potential more broadly, e.g., in farming, humanities. We aim to replace this tedious process through novel AI methods capable of generating DNNs that can perform significantly better and at a lower computational cost than manually designed DNNs. We further expand this idea to so ....Democratisation of Deep Learning: Neural Architecture Search at Low Cost. The need to manually design Deep Learning-based Neural Networks (DNNs) limits their usage to AI experts and hinders the exploitation of their true potential more broadly, e.g., in farming, humanities. We aim to replace this tedious process through novel AI methods capable of generating DNNs that can perform significantly better and at a lower computational cost than manually designed DNNs. We further expand this idea to solve complex real-world problems with both labelled and unlabelled data found in various applications including energy and climate change. The expected outcomes include the novel AI methods, highly trained AI researchers and a number of critical applications that will bring significant benefits to Australia and the world.Read moreRead less
Housing energy efficiency transitions. This project aims to provide an analysis of housing retrofit and its links with household energy costs. It includes householders across eight global urban sites, as well as the businesses that supply retrofit services. The project will analyse the retrofit experience of both energy poor and other households, providing an internationally significant evidence base. Outcomes include a robust empirical evidence base on the implications of retrofit for househol ....Housing energy efficiency transitions. This project aims to provide an analysis of housing retrofit and its links with household energy costs. It includes householders across eight global urban sites, as well as the businesses that supply retrofit services. The project will analyse the retrofit experience of both energy poor and other households, providing an internationally significant evidence base. Outcomes include a robust empirical evidence base on the implications of retrofit for households to tailor actions that will shape the lives of residents in Australian households.Read moreRead less
Australia's Resilience to Recession. This project aims to study why Australia differs from its OECD peers in that it has not had a recession for 27 years. It intends to generate knowledge by using economic models to solve 3 puzzles relating to Australia’s success: (i) why did foreign financial market shocks not spill over to the economy?; (ii) how has the resource curse that affects economies with a booming resource sector been avoided?; and (iii) what makes Australia special? Expected outcomes ....Australia's Resilience to Recession. This project aims to study why Australia differs from its OECD peers in that it has not had a recession for 27 years. It intends to generate knowledge by using economic models to solve 3 puzzles relating to Australia’s success: (i) why did foreign financial market shocks not spill over to the economy?; (ii) how has the resource curse that affects economies with a booming resource sector been avoided?; and (iii) what makes Australia special? Expected outcomes include the development of theoretical and empirical models that reflect the unique features of the Australian economy. This should provide significant benefits, including guidance to Australian and international policymakers on macroeconomic policies for resource-rich countries.Read moreRead less
Global wavefront propagation and non-elliptic Fredholm theory. Many significant phenomena in the natural world are described by partial differential equations that involve evolution in time. This project aims to develop new mathematical methods, involving recently discovered global wavefront set analysis and Fredholm theory, to solve such equations. These methods aim to extend the range of equations that can be solved as well as yield more information about solutions, in particular, their long-t ....Global wavefront propagation and non-elliptic Fredholm theory. Many significant phenomena in the natural world are described by partial differential equations that involve evolution in time. This project aims to develop new mathematical methods, involving recently discovered global wavefront set analysis and Fredholm theory, to solve such equations. These methods aim to extend the range of equations that can be solved as well as yield more information about solutions, in particular, their long-time asymptotics.Read moreRead less
Evolution of Proterozoic multistage rift basins – key to mineral systems. This project will deliver a new quantitative and integrated exploratory framework for the mineral industry in Australia’s frontier sedimentary basins by integrating the latest advances in laboratory experimental tectonics with thermo-mechanical numerical, surface process and geophysical modelling. The project will use northern Australian basins as a natural laboratory to address the fundamental processes involved in the de ....Evolution of Proterozoic multistage rift basins – key to mineral systems. This project will deliver a new quantitative and integrated exploratory framework for the mineral industry in Australia’s frontier sedimentary basins by integrating the latest advances in laboratory experimental tectonics with thermo-mechanical numerical, surface process and geophysical modelling. The project will use northern Australian basins as a natural laboratory to address the fundamental processes involved in the development of sedimentary ore systems. The project will investigate how they can be detected by modern exploration techniques using a multidisciplinary approach with a team of experts with backgrounds in mineral and petroleum systems. Read moreRead less
Emotions and Employee Turnover: New Methods for Complex Dynamic Systems. This project aims to vastly improve the data-analytic capabilities of social and health researchers, while increasing knowledge about emotion dynamics and their link to employee turnover. By drawing on and advancing methods from ecology and applied physics, this project plans to investigate the role that individual emotions play in employee turnover with new quantitative methods for characterising and testing causality in c ....Emotions and Employee Turnover: New Methods for Complex Dynamic Systems. This project aims to vastly improve the data-analytic capabilities of social and health researchers, while increasing knowledge about emotion dynamics and their link to employee turnover. By drawing on and advancing methods from ecology and applied physics, this project plans to investigate the role that individual emotions play in employee turnover with new quantitative methods for characterising and testing causality in complex dynamic systems. The expected outcomes include an improved capacity for researchers, managers, and policy makers to understand complex organisational, economic, and health systems. This will provide immediate societal benefits by informing the development and deployment of targeted interventions in such systems.Read moreRead less
A novel and efficient approach for optimisation involving iterative solvers. Computationally expensive simulations involving iterative solvers are increasingly being used in industry to assess performance of products and processes. Repeated use of such simulations is necessary to identify optimum solutions. Even with today's computing power, many such tasks remain computationally prohibitive. This project presents a novel approach to solve optimisation problems involving iterative solvers with l ....A novel and efficient approach for optimisation involving iterative solvers. Computationally expensive simulations involving iterative solvers are increasingly being used in industry to assess performance of products and processes. Repeated use of such simulations is necessary to identify optimum solutions. Even with today's computing power, many such tasks remain computationally prohibitive. This project presents a novel approach to solve optimisation problems involving iterative solvers with limited computing budget. A wide range of industries involved in product and process design would gain a significant competitive advantage from this unique technical innovation. In addition, this technology will be invaluable to uncover and understand complex natural phenomena.Read moreRead less