Subband centroids and deep neural networks for robust speech recognition. This project aims to improve the robustness and accuracy of automatic speech and speaker recognition systems. Though these systems work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. To overcome this problem, this project proposes a missing-feature approach for robust speech and speaker recognition. This approach is expected to make th ....Subband centroids and deep neural networks for robust speech recognition. This project aims to improve the robustness and accuracy of automatic speech and speaker recognition systems. Though these systems work reasonably well in noise-free environments, their performance deteriorates drastically even in the presence of a small amount of noise. To overcome this problem, this project proposes a missing-feature approach for robust speech and speaker recognition. This approach is expected to make the speech and speaker recognition systems less sensitive to additive background noise and make them more useful in telecommunications and business.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
Maximising value in underground mine planning. Mining is crucial to Australia’s economy, contributing 8 per cent of GDP and 55 per cent of the value of goods exported. Working with mining companies Rand and Tribune, this project tackles issues faced in underground mine planning. While integrated optimisation of design and production in open cut mining is well established, no equivalent capability is available for underground mines. This project aims to develop innovative techniques to optimise t ....Maximising value in underground mine planning. Mining is crucial to Australia’s economy, contributing 8 per cent of GDP and 55 per cent of the value of goods exported. Working with mining companies Rand and Tribune, this project tackles issues faced in underground mine planning. While integrated optimisation of design and production in open cut mining is well established, no equivalent capability is available for underground mines. This project aims to develop innovative techniques to optimise the design of the access network and the production scheduling in an underground mine in order to maximise value over the life of the operation. The outcome intends to be a new strategic software tools for the sector, underpinning increased efficiency and sustainability of Australian mines as well as international competitiveness.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE130100457
Funder
Australian Research Council
Funding Amount
$360,945.00
Summary
Dynamic fracturing in shale rock through coupled continuum-discontinuum modelling. The research includes modelling the grain level fracturing of shale rock under dynamic loads. The outputs will have a direct impact on the development and optimisation of rock drilling and rock cutting technologies and will improve the operational efficiencies in which rock excavations are conducted.
Human Cues for Robot Navigation. The world has many navigational cues for the benefit of humans: sign posts, maps and the wealth of information on the internet. Yet, to date, robotic navigation has made little use of this abundant symbolic information as a resource. This project will develop a robot navigation system that can navigate using information beyond the robot's range sensors by incorporating knowledge gained by reading room labels, following human route directions or interpreting maps ....Human Cues for Robot Navigation. The world has many navigational cues for the benefit of humans: sign posts, maps and the wealth of information on the internet. Yet, to date, robotic navigation has made little use of this abundant symbolic information as a resource. This project will develop a robot navigation system that can navigate using information beyond the robot's range sensors by incorporating knowledge gained by reading room labels, following human route directions or interpreting maps found on the web. This project will demonstrate the robot's navigation ability by comparing its performance with a human as it learns to find its way around campus by asking for directions, reading signs and maps, and searching the internet for clues.Read moreRead less
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
Maximisation of value in underground mine access design. This project represents a major advance in the problem of optimising the mine value associated with the access infrastructure of underground mines and providing powerful planning tools for management. The usefulness to the mining industry of the methods and algorithms the project is pioneering lies in their accuracy, flexibility and generality. Not only can they be used for benchmarking value in the design of specific mines, but they can ....Maximisation of value in underground mine access design. This project represents a major advance in the problem of optimising the mine value associated with the access infrastructure of underground mines and providing powerful planning tools for management. The usefulness to the mining industry of the methods and algorithms the project is pioneering lies in their accuracy, flexibility and generality. Not only can they be used for benchmarking value in the design of specific mines, but they can also determine the profitability or viability of mines under the use of new technologies. This is an important project for ensuring that Australia's mining industry remains efficient and internationally competitive. Given Australia’s economic dependence on mineral resources, it will also benefit the country as a whole.Read moreRead less
Multi-modal virtual microscopy for quantitative diagnostic pathology. This project will contribute to the next generation of virtual microscopy systems that provide innovative features capable of significantly increasing the adoption of digital imaging technology throughout the field of diagnostic pathology. These tools will especially contribute to the screening and diagnosis of cervical, lung and bladder cancer.
Benign recovery of precious metals from deep pristine environments. This project aims to extract precious metals from natural deposits conventional mining methods cannot reach. Glycine-peroxide systems can dissolve precious metals without pollution. Understanding these systems’ behaviour in natural orebodies could lead to in-situ leaching methods that complement conventional mining, especially in low grade deposits. This project intends to use a modern scientific workflow based on exploratory, d ....Benign recovery of precious metals from deep pristine environments. This project aims to extract precious metals from natural deposits conventional mining methods cannot reach. Glycine-peroxide systems can dissolve precious metals without pollution. Understanding these systems’ behaviour in natural orebodies could lead to in-situ leaching methods that complement conventional mining, especially in low grade deposits. This project intends to use a modern scientific workflow based on exploratory, descriptive and explanatory phases to model the coupled multi-physics of precious metals transport, introduce a high performance computing strategy for in-situ leaching, develop an experimental protocol that explains the recovery mechanisms, and propose optimal leaching patterns that maximise productivity.Read moreRead less
New techniques to detect fetal heart abnormalities. Australia’s national fetal death rate is 6.7 per one thousand births. In Australia’s Indigenous community it surges to 12.3 deaths per one thousand births. Early diagnosis (and management) of abnormal fetu.ses with cardiac defects will go a long way in reducing these numbers. The proposed technology will help set up easy-to-use systems for fetal cardiac abnormality screening and reduce fetal deaths and congenital heart disease burden in adult l ....New techniques to detect fetal heart abnormalities. Australia’s national fetal death rate is 6.7 per one thousand births. In Australia’s Indigenous community it surges to 12.3 deaths per one thousand births. Early diagnosis (and management) of abnormal fetu.ses with cardiac defects will go a long way in reducing these numbers. The proposed technology will help set up easy-to-use systems for fetal cardiac abnormality screening and reduce fetal deaths and congenital heart disease burden in adult life. This project will also provide domain trained researchers with cutting edge international academic and industry expertise.Read moreRead less