Differential Evolution Framework for Intelligent Charging Scheduling. Smart charging scheduling is a vital challenge as dynamic environment with traffic networks and various unexpected issues. This project aims to develop a differential evolution framework for intelligent charging scheduling. The framework consists of a comprehensive charging scheduling model with various road networks and factors. The project outcomes include a distributed evolutionary computation framework, differential evolut ....Differential Evolution Framework for Intelligent Charging Scheduling. Smart charging scheduling is a vital challenge as dynamic environment with traffic networks and various unexpected issues. This project aims to develop a differential evolution framework for intelligent charging scheduling. The framework consists of a comprehensive charging scheduling model with various road networks and factors. The project outcomes include a distributed evolutionary computation framework, differential evolution algorithms, and cooperative co-evolutionary strategies. The outcome results will be demonstrated by practical evaluations over public datasets and comparisons to related works. The project is beneficial to the nation in both theory of artificial intelligence techniques and applications of real transport systems.Read moreRead less
Rapid point-of-care detection of genomic variations for personalised medicine. Selecting treatment based on a person’s genetic profile can improve drug safety and efficacy, but the application is hampered by the inconvenience, slow result turnaround and high cost of current lab-based tests. Full implementation of personalised medicine in clinical practice requires a point-of-care testing system. This project aims to overcome the challenges involved in developing such a system by validating novel ....Rapid point-of-care detection of genomic variations for personalised medicine. Selecting treatment based on a person’s genetic profile can improve drug safety and efficacy, but the application is hampered by the inconvenience, slow result turnaround and high cost of current lab-based tests. Full implementation of personalised medicine in clinical practice requires a point-of-care testing system. This project aims to overcome the challenges involved in developing such a system by validating novel rapid genotyping methods and developing ultrasensitive real-time DNA detection that will be integrated on a single chip platform to facilitate a small, low cost and reliable test device. The technology will be readily adaptable to areas where prompt access to genomic information is valuable, such as disease diagnosis and risk prediction.Read moreRead less
A novel platform-technology for long-term subcutaneous neurophysiology. This project aims to develop a novel miniature device for subcutaneous and tetherless brain sensing. It addresses the lack of a device solution for brain-sensing that combines ultra-long-term reliable sensing capability and small dimensions for minimally-invasive procedures. We achieve this through our novel electrode architecture that significantly enhances the quality and reliability of recorded brain signals. We introduce ....A novel platform-technology for long-term subcutaneous neurophysiology. This project aims to develop a novel miniature device for subcutaneous and tetherless brain sensing. It addresses the lack of a device solution for brain-sensing that combines ultra-long-term reliable sensing capability and small dimensions for minimally-invasive procedures. We achieve this through our novel electrode architecture that significantly enhances the quality and reliability of recorded brain signals. We introduce a platform technology designed for subscalp anatomy with future use in various brain-machine interfacing applications relying on reliable, long-term and easy-to-implant systems. This project's device manufacturing, training, and intellectual property are expected to strengthen Australia's position in bioelectronics.Read moreRead less
Efficient and effective methods for classifying massive time series data. This project aims to transform the theory and practice of time series classification. The current state of the art cannot handle the massive numbers of time series that describe many critical problems facing humanity, such as disease transmission and climate change. This project seeks to develop methods that can analyse dynamic processes at global scale, delivering the most accurate classifiers feasible within a given comp ....Efficient and effective methods for classifying massive time series data. This project aims to transform the theory and practice of time series classification. The current state of the art cannot handle the massive numbers of time series that describe many critical problems facing humanity, such as disease transmission and climate change. This project seeks to develop methods that can analyse dynamic processes at global scale, delivering the most accurate classifiers feasible within a given computational budget. Expected outcomes of this project include efficient, effective and broadly applicable time series classification technologies. This should provide significant benefits to myriad sectors, transforming data science for time series problems and supporting innovation in industry, commerce and government.Read moreRead less
Fast effective clustering technologies for highly dynamic massive networks. Clustering is a fundamental data mining and analysis task. In an interconnected evolving world, friendships and information flows are modelled as large dynamic networks. Structural clustering and correlation clustering are important and well-studied approaches for static networks; for evolving networks, where links appear and disappear over time, we lack efficient techniques. Anticipated outcomes are new practical cluste ....Fast effective clustering technologies for highly dynamic massive networks. Clustering is a fundamental data mining and analysis task. In an interconnected evolving world, friendships and information flows are modelled as large dynamic networks. Structural clustering and correlation clustering are important and well-studied approaches for static networks; for evolving networks, where links appear and disappear over time, we lack efficient techniques. Anticipated outcomes are new practical clustering algorithms for dynamic networks – with performance guarantees of efficiency and clustering quality – and prototype software, guiding us to pick a good clustering. Expected benefits include better understanding of spread in evolving social networks, accelerating the software testing cycle, and improved topic detection.Read moreRead less
Diamond glass: An all-carbon technology for neural networks and biosensing. This project aims to use plasma deposition to synthesise diamond glass with the highest purity and the most diamond-like character so that it meets the strict requirements for emerging device applications. The extreme properties of diamond glass arise from the diamond-like bonding of the majority of its atoms. This amorphous, wide bandgap semiconductor is also the hardest known glass. The maximum diamond-like content pos ....Diamond glass: An all-carbon technology for neural networks and biosensing. This project aims to use plasma deposition to synthesise diamond glass with the highest purity and the most diamond-like character so that it meets the strict requirements for emerging device applications. The extreme properties of diamond glass arise from the diamond-like bonding of the majority of its atoms. This amorphous, wide bandgap semiconductor is also the hardest known glass. The maximum diamond-like content possible in diamond glass coatings is unknown, so determining its ultimate performance is difficult. Expected applications include medical diagnostics, non-volatile memories and programmable chips.Read moreRead less
Knowledge Graph-driven Software Vulnerability Risk Discovery and Assessment. This project aims to alleviate cyberattacks which are increasingly being crafted to attack software vulnerabilities and weaknesses by utilising advanced knowledge graphs and deep learning techniques. This project expects to construct an innovative software vulnerability knowledge graph and develop advanced graph-based algorithms and models. Expected outcomes of this project include the enhanced capacity to defend agains ....Knowledge Graph-driven Software Vulnerability Risk Discovery and Assessment. This project aims to alleviate cyberattacks which are increasingly being crafted to attack software vulnerabilities and weaknesses by utilising advanced knowledge graphs and deep learning techniques. This project expects to construct an innovative software vulnerability knowledge graph and develop advanced graph-based algorithms and models. Expected outcomes of this project include the enhanced capacity to defend against cyberattacks for both organisations and individuals in Australia and beyond, theory development in graph theory, refined graph neural network models and improved graph transfer learning algorithms.Read moreRead less
Fast Reconstruction and Real-time Rendering of Immersive Light Field Video. This project aims to develop new learning-based methods for reconstructing and rendering 3D immersive videos from multi-view 2D videos. The project expects to generate new knowledge in the areas of data mining, multimedia, pattern recognition and deep learning. Expected outcomes of this project include new deep neural networks to represent 3D videos, neural methods for high-fidelity video rendering and efficient 3D video ....Fast Reconstruction and Real-time Rendering of Immersive Light Field Video. This project aims to develop new learning-based methods for reconstructing and rendering 3D immersive videos from multi-view 2D videos. The project expects to generate new knowledge in the areas of data mining, multimedia, pattern recognition and deep learning. Expected outcomes of this project include new deep neural networks to represent 3D videos, neural methods for high-fidelity video rendering and efficient 3D video reconstruction and rendering algorithms. This should provide significant benefits to a diverse range of practical applications, such as autonomous driving, virtual reality, healthcare, advanced manufacturing, and many other 3D applications.Read moreRead less
Identifying and Tracking Influential Events in Large Social Networks. This project aims to invent a novel model and techniques for identifying and tracking influential events in large and dynamic social networks in real time. The proposed model would take into account the structure and content of social networks, and the influence of events. The project also plans to develop efficient strategies for identifying and tracking events in large and dynamic social network environments based on the mod ....Identifying and Tracking Influential Events in Large Social Networks. This project aims to invent a novel model and techniques for identifying and tracking influential events in large and dynamic social networks in real time. The proposed model would take into account the structure and content of social networks, and the influence of events. The project also plans to develop efficient strategies for identifying and tracking events in large and dynamic social network environments based on the model, In particular, the project plans to investigate flexible social network query methods to make users’ event search easy. Finally the project plans to build an evaluation system to demonstrate the efficiency of the algorithms and effectiveness of the model.Read moreRead less
Biclique discovery in Big Data. This project aims to design algorithms to capture Big Data. Biclique is a popular graph model that can capture important cohesive structures in many applications. However, traditional biclique discovery algorithms which only focus on simple, small-scale, static and deterministic data are inadequate in the era of Big Data where data has Variety (various formats), Volume (large quantity), Velocity (dynamic update) and Veracity (uncertainty). This project expects to ....Biclique discovery in Big Data. This project aims to design algorithms to capture Big Data. Biclique is a popular graph model that can capture important cohesive structures in many applications. However, traditional biclique discovery algorithms which only focus on simple, small-scale, static and deterministic data are inadequate in the era of Big Data where data has Variety (various formats), Volume (large quantity), Velocity (dynamic update) and Veracity (uncertainty). This project expects to benefit real applications in both public and private sectors and add value to Australian manufactured products.Read moreRead less