Automatic detection of the circle of Willis in neuro-images using multi-scale gradient calculation and knowledge-based genetic algorithms. Stroke is the third most common cause of death and a major contributor to long term disability in Australia. The most efficient way of preventing stroke from happening is to detect related symptoms early. The group of cerebral blood vessels that closely related to strokes is the circle of Willis (CoW). We build a system that can automatically detect and quan ....Automatic detection of the circle of Willis in neuro-images using multi-scale gradient calculation and knowledge-based genetic algorithms. Stroke is the third most common cause of death and a major contributor to long term disability in Australia. The most efficient way of preventing stroke from happening is to detect related symptoms early. The group of cerebral blood vessels that closely related to strokes is the circle of Willis (CoW). We build a system that can automatically detect and quantify CoW in neuroimages, providing ways of preventing strokes from happening. The project will enhance Australia¡¯s leading position in promoting and maintaining good health, especially in preventive healthcare.Read moreRead less
Analysing Iterative Machine Learning Algorithms with Information Geometric Methods. Online machine learning problems arise from situations where data is provided a point at a time. There are many classical algorithms for solving such problems based on the principle of stochastic gradient descent. Recent research by the CIs and others have thrown up interesting but diverse geometric connections that offer new insights. The proposed research aims to integrate the understanding of these algori ....Analysing Iterative Machine Learning Algorithms with Information Geometric Methods. Online machine learning problems arise from situations where data is provided a point at a time. There are many classical algorithms for solving such problems based on the principle of stochastic gradient descent. Recent research by the CIs and others have thrown up interesting but diverse geometric connections that offer new insights. The proposed research aims to integrate the understanding of these algorithms with the aim of designing algorithms better able to exploit prior knowledge, and to extend existing algorithms to new problem domains thus offering well principled and well understood algorithms for solving a variety of novel online problems.Read moreRead less
Behaviour Bootstrapping for Ad Hoc, Heterogeneous Robot Swarms. This project aims to develop algorithms to permit groups of robots to evolve coordinated, collective, swarm behaviours. Groups of robots will be conceptualised as developmental swarm organisms with an initially limited set of behaviours, but equipped with structures and processes to permit them to evolve new behaviours. This project expects to deliver the next generation of computational intelligence technologies to enable humans to ....Behaviour Bootstrapping for Ad Hoc, Heterogeneous Robot Swarms. This project aims to develop algorithms to permit groups of robots to evolve coordinated, collective, swarm behaviours. Groups of robots will be conceptualised as developmental swarm organisms with an initially limited set of behaviours, but equipped with structures and processes to permit them to evolve new behaviours. This project expects to deliver the next generation of computational intelligence technologies to enable humans to harness large groups of robots for new kinds of transport and inspection tasks in smart cities, smart farming and defence. The expected outcomes of the project include new software frameworks for distributed developmental learning, extending developmental robotics to evolutionary robot swarms. Read moreRead less
Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected ....Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected outcomes include the
development of software that allows the solution of hitherto unsolved machine
learning problems, and the ability to solve problems larger than those solvable
by the current generation of machine learning tools.Read moreRead less
Data structures which change with time, a machine learning approach. Visibility of web pages, based on page importance, on the Internet controls their accessibility by users which is critical for e-Commerce applications. The page importance depends on its contents and its link structure to other web pages, both of which can be time varying. This project proposes a novel model in which time varying aspects of the changes to contents and their link structures are captured, thus allowing us a bette ....Data structures which change with time, a machine learning approach. Visibility of web pages, based on page importance, on the Internet controls their accessibility by users which is critical for e-Commerce applications. The page importance depends on its contents and its link structure to other web pages, both of which can be time varying. This project proposes a novel model in which time varying aspects of the changes to contents and their link structures are captured, thus allowing us a better understanding of how these influence the page importance over time. It will also allow us insight on how to improve the visibility of web pages.Read moreRead less
Investigations in Learning Algorithms for Web Page Scoring Systems. Modification of web page scores to satisfy requirements, e.g., one page should have a higher page score than another, a home page should have higher score than any other pages in the same site, using modifications of the forcing function, and the link connectivity matrix respectively of the PageRank equation will be studied. By clustering web pages either by ranks or by scores will help overcome issues of scale and complexity wh ....Investigations in Learning Algorithms for Web Page Scoring Systems. Modification of web page scores to satisfy requirements, e.g., one page should have a higher page score than another, a home page should have higher score than any other pages in the same site, using modifications of the forcing function, and the link connectivity matrix respectively of the PageRank equation will be studied. By clustering web pages either by ranks or by scores will help overcome issues of scale and complexity which are required for the live world wide web. Outcomes will provide a rational basis together with practical methods for modifying web page scores by a web site administrator.Read moreRead less
Machine education for trusted multi-skilled evolutionary learners . Transforming data assets into organisational knowledge assets sits in the hands of a few, highly specialised, data scientists. The aim of this research is to design educational instruments to support non-experts to teach artificial intelligence (AI) systems in a similar way to educating human teachers to teach human learners. The significance of the project lies in affording the wider smart, but not necessarily AI expert, commun ....Machine education for trusted multi-skilled evolutionary learners . Transforming data assets into organisational knowledge assets sits in the hands of a few, highly specialised, data scientists. The aim of this research is to design educational instruments to support non-experts to teach artificial intelligence (AI) systems in a similar way to educating human teachers to teach human learners. The significance of the project lies in affording the wider smart, but not necessarily AI expert, community the ability to contribute to growing our knowledge-based society in a safe, transparent and trustworthy manner. Outcomes will include innovative instruments to teach machines, novel knowledge creation, trusted and transparent AI systems, and a new generation of human teachers specialised in educating AI systems.Read moreRead less
Non-invasive prediction of adverse neural events using brain wave activity. This project aims to develop intelligent decision-making systems for non-invasive identification of adverse neural events (fatigue/freezing of gait) through real-time monitoring of brain wave activity. Analyses of the effectiveness of the changes in physiological parameters associated with electroencephalography (EEG) signals, advanced biomedical instrumentation, and optimal computational intelligence will form a basis f ....Non-invasive prediction of adverse neural events using brain wave activity. This project aims to develop intelligent decision-making systems for non-invasive identification of adverse neural events (fatigue/freezing of gait) through real-time monitoring of brain wave activity. Analyses of the effectiveness of the changes in physiological parameters associated with electroencephalography (EEG) signals, advanced biomedical instrumentation, and optimal computational intelligence will form a basis for the development of platform technology capable of monitoring and detection of neural health status. Success is expected to yield a new generation of smart dynamic non-invasive systems that will be critical for developing effective solutions to counter life threating conditions for a large cross section of the Australian population.Read moreRead less
Memetic algorithms and adaptive memory metaheuristics for large scale combinatorial optimisation problems arising in biomarker discovery. Despite modern supercomputers, the world depends on combinatorial optimisation, the branch of mathematics and computer science that involves finding optimal solutions when it is impossible to enumerate all solutions. We bring complementary skills to address the core set of the five most challenging problems arising from novel biotechnologies.
Unleashing the power of a supernetwork-driven approach for bioinformatics. Supernetworks are built “above and beyond” existing networks. In bioinformatics they arise from the integration of a set of networks with different types of nodes and edges. While large companies and governments have already understood the importance of decision problems in supernetworks, the power of this perspective has not yet been exploited in the life sciences. Using supercomputer-based approaches together with memet ....Unleashing the power of a supernetwork-driven approach for bioinformatics. Supernetworks are built “above and beyond” existing networks. In bioinformatics they arise from the integration of a set of networks with different types of nodes and edges. While large companies and governments have already understood the importance of decision problems in supernetworks, the power of this perspective has not yet been exploited in the life sciences. Using supercomputer-based approaches together with memetic algorithms, this project will address the first key areas that will lead to smart information use of existing networks in distributed databases. This project will deliver the next generation of algorithms for network alignment, identification of connected-cohesive subnetworks and embedding large graphs in multi-planar structures.Read moreRead less