Deep reinforcement learning for discovering and visualising biomarkers. This project aims to develop novel methods for discovering and visualising optimal bio-markers from chest computed tomography images based on extensions of recently developed deep reinforcement learning techniques. The extensions proposed in this project will advance medical image analysis by allowing an efficient analysis of large dimensionality inputs in their original high resolution. In addition, this project will be the ....Deep reinforcement learning for discovering and visualising biomarkers. This project aims to develop novel methods for discovering and visualising optimal bio-markers from chest computed tomography images based on extensions of recently developed deep reinforcement learning techniques. The extensions proposed in this project will advance medical image analysis by allowing an efficient analysis of large dimensionality inputs in their original high resolution. In addition, this project will be the first approach capable of discovering previously unknown biomarkers associated with important clinical outcomes. The project will validate the approach on a real-world case study data set concerning the prediction of five-year survival of chronic disease.Read moreRead less
Flotation in high salt concentration: resolving critical knowledge gaps relating the ion effect on bubble production and behavior. Flotation separation of coal and mineral particles by attaching to rising air bubbles is significantly affected in high salt concentration but its exact mechanism still remains unclear. This project employs state-of-the-art surface sensitive spectroscopy and modeling tools to investigate how salt ions influence drainage and rupture of liquid films between two bubbles ....Flotation in high salt concentration: resolving critical knowledge gaps relating the ion effect on bubble production and behavior. Flotation separation of coal and mineral particles by attaching to rising air bubbles is significantly affected in high salt concentration but its exact mechanism still remains unclear. This project employs state-of-the-art surface sensitive spectroscopy and modeling tools to investigate how salt ions influence drainage and rupture of liquid films between two bubbles, and bubble production and behaviour relevant to the flotation processes. The research will develop better water use for coal and mineral flotation to reduce reagent usage and environmental impacts of water pollution. The project will contribute significantly to knowledge advancement in the coal and mineral industry.Read moreRead less
A new role for vibration analysis in gear wear modelling and prediction. This project aims to improve prediction of the remaining useful life of gears. Gears are widely used in industry and transport. This project aims to integrate the two main methods of gear condition monitoring, vibration and oil analysis, and perform model-based wear prediction with the tribology and dynamic models continually updated on the basis of measured wear debris and vibration. New signal processing tools should allo ....A new role for vibration analysis in gear wear modelling and prediction. This project aims to improve prediction of the remaining useful life of gears. Gears are widely used in industry and transport. This project aims to integrate the two main methods of gear condition monitoring, vibration and oil analysis, and perform model-based wear prediction with the tribology and dynamic models continually updated on the basis of measured wear debris and vibration. New signal processing tools should allow estimation of relatively weak friction forces, previously neglected, as an important prognostic tool. This would allow detailed root cause analysis and prediction of remaining useful life. Improvements in gear prognosis would have safety and economic benefits by eliminating unforeseen catastrophic failures and optimising maintenance schedules.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
Ecologically responsible mining to fuel a green energy transition. An energy transition is key to tackling climate change. However, renewable energy is mineral intensive and boosting its supply may create new mining threats to biodiversity. This project aims to facilitate strategic development of ecologically responsible mining. It expects to reveal where new mines will be needed to meet future energy demand, and create innovative tools to predict and mitigate threats to plants and animals. Expe ....Ecologically responsible mining to fuel a green energy transition. An energy transition is key to tackling climate change. However, renewable energy is mineral intensive and boosting its supply may create new mining threats to biodiversity. This project aims to facilitate strategic development of ecologically responsible mining. It expects to reveal where new mines will be needed to meet future energy demand, and create innovative tools to predict and mitigate threats to plants and animals. Expected outcomes include an improved ability to inform sustainable climate and energy policies, leading to strategic investment decisions, cleaner mineral supply chains and conservation outcomes that capture valuable environmental and social benefits and create a competitive advantage for Australia’s mining sector.Read moreRead less
Market segmentation methodology: attacking the 'Too Hard' basket. Businesses embrace market segmentation to identify and target clients. However, poor segmentation analysis leads to poor segment choice. This project will develop tools to improve segmentation analysis and will test the resulting tools in tourism, foster care and climate change mitigating behaviours, and produce usable, transferable recommendations.
Poro-elastic, single domain model of wave-induced transport and transformation of pollutants in coastal sediments. The sediments in many bays and estuaries in Australia are contaminated by pollutants due to discharge of waste from the river, groundwater or/and ocean outfall. Most previous research has had a multi-domain approach and have ignored the wave-dirven advective flow and effects of soil behaviour in coastal sediment. In this study, we will couple the procedure of pollutant transport ne ....Poro-elastic, single domain model of wave-induced transport and transformation of pollutants in coastal sediments. The sediments in many bays and estuaries in Australia are contaminated by pollutants due to discharge of waste from the river, groundwater or/and ocean outfall. Most previous research has had a multi-domain approach and have ignored the wave-dirven advective flow and effects of soil behaviour in coastal sediment. In this study, we will couple the procedure of pollutant transport near the sediment-water interface by a single domain approach, and link wave-dirven advective flow and contaminant in marine sediments. The research outcomes will provide a better prediction of the transformation behaviour of pollutants in contaminated sediments.Read moreRead less
Rigorous Three Dimensional Plasticity Solutions for Soil and Rock Slopes. Slope failures and landslides are a persistent cause of economic loss in Australia. Damages resulting from landslides include both property damage and loss of life. One such recent catastrophic slope failure is the landslide that occurred at Thredbo Village in New South Wales in 1997. This monumental landslide resulted in the deaths of 18 people and was considered by the coroner as the worst natural disaster in Australian ....Rigorous Three Dimensional Plasticity Solutions for Soil and Rock Slopes. Slope failures and landslides are a persistent cause of economic loss in Australia. Damages resulting from landslides include both property damage and loss of life. One such recent catastrophic slope failure is the landslide that occurred at Thredbo Village in New South Wales in 1997. This monumental landslide resulted in the deaths of 18 people and was considered by the coroner as the worst natural disaster in Australian history. The primary aim of this research project is to apply recently developed computational tools to better understand 3D slope behaviour and to develop rigorous stability solutions that can be used by design engineers. A better understanding of 3D slope failure will lead to more economic and safer slope designs.Read moreRead less
Coupling models for ocean waves, groundwater and porous seabeds interaction. The ocean waves, groundwater flow and porous seabeds interaction problem is vital for erosion control, saltily and biological activities in coastal regions. Most previous research has investigated the problem from individual aspects, rather than a coupling concept. In this study, we will develop advanced theoretical models for procedures of waves propagation, water table fluctuations and soil behaviour in a porous seabe ....Coupling models for ocean waves, groundwater and porous seabeds interaction. The ocean waves, groundwater flow and porous seabeds interaction problem is vital for erosion control, saltily and biological activities in coastal regions. Most previous research has investigated the problem from individual aspects, rather than a coupling concept. In this study, we will develop advanced theoretical models for procedures of waves propagation, water table fluctuations and soil behaviour in a porous seabed, and couple them in a model. A series of experiments will be conducted for the verification of the theoretical findings. The research outcomes will provide a better understanding of the interaction between ocean wave, groundwater flow and porous seabeds.Read moreRead less
Low-cost Sensing Methods and Hybrid Learning Models. This project aims to revolutionise the theory and practice of sensing and monitoring by developing novel Artificial Intelligence and Internet of Things technologies. This project expects to generate new knowledge in the area of Artificial Intelligence of Things by combining sensing, machine learning, and big data analytics. Expected outcomes of this project include novel low-cost sensing methods and new hybrid machine learning models for predi ....Low-cost Sensing Methods and Hybrid Learning Models. This project aims to revolutionise the theory and practice of sensing and monitoring by developing novel Artificial Intelligence and Internet of Things technologies. This project expects to generate new knowledge in the area of Artificial Intelligence of Things by combining sensing, machine learning, and big data analytics. Expected outcomes of this project include novel low-cost sensing methods and new hybrid machine learning models for predictive sensory data analytics. This should provide significant benefits, such as substantially reduced operating and service costs and improved accuracy for real-time monitoring in the fields where cheap-to-implement and easy-to-service monitoring systems over large geographical areas are imperative.Read moreRead less