Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques ....Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques that use large amounts of unlabeled data to enhance performance. Our design takes advantage of additional information available for marine imagery such as geolocation and remote sensing context. We will explore how these representations can guide additional sampling and improve performance in classification tasks.Read moreRead less
Tuning parallel applications on software-defined supercomputers. Supercomputers are used by many Australian industries and laboratories to make better products and perform critical predictions, and it is essential that codes operate efficiently. This project aims to assist programmers in identifying performance bottlenecks in their code quickly and easily. The project expects to supersede the current methods, which are often complex and time-consuming, by developing innovative software tools and ....Tuning parallel applications on software-defined supercomputers. Supercomputers are used by many Australian industries and laboratories to make better products and perform critical predictions, and it is essential that codes operate efficiently. This project aims to assist programmers in identifying performance bottlenecks in their code quickly and easily. The project expects to supersede the current methods, which are often complex and time-consuming, by developing innovative software tools and techniques. The expected outcomes include novel software, verified by industry partners in real world case studies, ranging from life sciences to hypersonic transport. This should provide significant benefits, including the capacity for Australian industries to access world-class supercomputing technology.Read moreRead less
Improving the Performance, Scalability and Reliability of the Linux Operating System. This project aims to improve the scalability of the Linux operating system to large systems without loss of performance on small, embedded, systems. It will improve Linux robustness and security by de-privileging particularly error-prone code, such as device drivers, without undue impact on performance. It will improve configurability and ease tuning by making critical components, such as processor, disk and me ....Improving the Performance, Scalability and Reliability of the Linux Operating System. This project aims to improve the scalability of the Linux operating system to large systems without loss of performance on small, embedded, systems. It will improve Linux robustness and security by de-privileging particularly error-prone code, such as device drivers, without undue impact on performance. It will improve configurability and ease tuning by making critical components, such as processor, disk and memory schedulers, pluggable and their policies controllable at user level. It will investigate the feasibility and benefits of user-level file systems and processor and memory scheduling and will demonstrate that these can improve system reliability without undermining performance.Read moreRead less
Operating systems meeting the challenges of modern computer architectures. This project will develop operating system techniques that allow extracting the best performance out of modern computer architectures. It will concentrate on the latest architecture, Itanium, whose innovative features make it a particular challenge for operating systems. The techniques will be implemented in the open source Linux operating system and will result in significantly reduced operating system overheads and enh ....Operating systems meeting the challenges of modern computer architectures. This project will develop operating system techniques that allow extracting the best performance out of modern computer architectures. It will concentrate on the latest architecture, Itanium, whose innovative features make it a particular challenge for operating systems. The techniques will be implemented in the open source Linux operating system and will result in significantly reduced operating system overheads and enhanced application performance.Read moreRead less
Dataparallel Programming for Multicore Processors. The proposed project will contribute to the development of frontier technologies to help build Australian industries. The project is designed to unlock significant performance improvements with current and future multicore (processor) computer architectures. This potential performance improvement can be achieved with parallel programming models. This is crucial for ICT applications in performance hungry areas, such as biotechnology, finance, mul ....Dataparallel Programming for Multicore Processors. The proposed project will contribute to the development of frontier technologies to help build Australian industries. The project is designed to unlock significant performance improvements with current and future multicore (processor) computer architectures. This potential performance improvement can be achieved with parallel programming models. This is crucial for ICT applications in performance hungry areas, such as biotechnology, finance, multi-media, and 'info-tainment'. The project will also provide research training and increase local expertise in parallel programming for multicore processors, an area that is quickly growing in importance.Read moreRead less
Autonomous repeatable surveys for long term monitoring of marine habitats. Australia has committed to using marine resources in a sustainable manner and to conserve the biodiversity of its marine habitats. In order to manage its marine environment effectively, marine scientists, managers and policy makers require timely and accurate information on the state of the environment. Current knowledge and techniques are limited and will have difficulty scaling to satisfy Australia's needs. A monitorin ....Autonomous repeatable surveys for long term monitoring of marine habitats. Australia has committed to using marine resources in a sustainable manner and to conserve the biodiversity of its marine habitats. In order to manage its marine environment effectively, marine scientists, managers and policy makers require timely and accurate information on the state of the environment. Current knowledge and techniques are limited and will have difficulty scaling to satisfy Australia's needs. A monitoring system that relies on machines to perform a substantial fraction of survey work and basic data analysis can scale more easily and provide more information at lower costs. Read moreRead less
Developing a personalised Music Affect Recommender System. The project aims to develop a personalised music recommender system using perceived tone quality, affect and liking. Recommender systems using prior verbal annotations and ratings are common (Amazon) but inappropriate for less popular music by unfamiliar artists, which lacks social use data. The project intends to build on work into perception of musical affect and its relation to loudness and tone quality; and the automation of the orga ....Developing a personalised Music Affect Recommender System. The project aims to develop a personalised music recommender system using perceived tone quality, affect and liking. Recommender systems using prior verbal annotations and ratings are common (Amazon) but inappropriate for less popular music by unfamiliar artists, which lacks social use data. The project intends to build on work into perception of musical affect and its relation to loudness and tone quality; and the automation of the organisation of digital libraries both by labels and acoustic content. Developing this, the project seeks to create a model that gives recommendations which accounts for an individual's preferences based on acoustic content, affect and liking. The system will be designed to update rapidly and to encourage exploration of familiar and unfamiliar music.Read moreRead less
Quality of Service in 3G Wireless Systems with Hybrid Networks. The increasing demand of providing Internet-based services over the mobile handsets has led to the transition from circuit-based 2G systems to packet-based network architectures in the emerging 3G systems. A major technical challenge for this paradigm shift is maintaining quality of services (QoS) for the existing data and voice and future Internet services such as streaming multimedia over such packet switching networks. This proje ....Quality of Service in 3G Wireless Systems with Hybrid Networks. The increasing demand of providing Internet-based services over the mobile handsets has led to the transition from circuit-based 2G systems to packet-based network architectures in the emerging 3G systems. A major technical challenge for this paradigm shift is maintaining quality of services (QoS) for the existing data and voice and future Internet services such as streaming multimedia over such packet switching networks. This project aims to investigate end-to-end QoS solutions in the 3G systems. Australian mobile Internet and voice carriers will significantly benefit from this technology.Read moreRead less
Achieving higher availability of storage subsystems through application of a self learning expert system. In todays global business environment the management, storage and security of enterprise data (data unavailability, data loss and corruption, systems performance) has become the heart of so-called Enterprise computing. The storage subsystems increasingly have become the critical subcomponent and single point of failure. Discovering the cause of failure in complex environments involving mul ....Achieving higher availability of storage subsystems through application of a self learning expert system. In todays global business environment the management, storage and security of enterprise data (data unavailability, data loss and corruption, systems performance) has become the heart of so-called Enterprise computing. The storage subsystems increasingly have become the critical subcomponent and single point of failure. Discovering the cause of failure in complex environments involving multiple vendors, machines, software products, topologies and cultures (languages) is in many cases time consuming and difficult resulting in unacceptable systems downtime and high maintenance costs. A more sophisticated tool is needed allowing the accumulation of knowledge, the ability to deal with complexity and change, the ability to interface with unlike knowledge bases and predict solution probability based on experience and feedback. Multi-lingual support and capability through the development of a Natural Language interface would provide a functional capability suited to managing enterprise data in todays global businesses.Read moreRead less
Learning the complexity of scientific knowledge about climate change with computer modelling and visualization technologies. This project provides benefits to the national priorities of a environmentally sustainable Australia; and frontier technologies for building and transforming Australian industries. The project helpins students in Australia more deeply understand the sciences that underlie environmental sustainability. Learning with modelling and visualization technologies will help student ....Learning the complexity of scientific knowledge about climate change with computer modelling and visualization technologies. This project provides benefits to the national priorities of a environmentally sustainable Australia; and frontier technologies for building and transforming Australian industries. The project helpins students in Australia more deeply understand the sciences that underlie environmental sustainability. Learning with modelling and visualization technologies will help students learn important scientific knowledge and prepare them for the use of frontier technologies that are becoming infused into the practices of scientists and professionals in many fields. This project also directly contributes to the national Digital Education Revolution initiative.Read moreRead less