A safety-preserving ecosystem for autonomous driving. In this project, Macquarie University will collaborate with UTS and SilverQuest to develop an innovative safety-preserving ecosystem for autonomous driving. This system will not only be adopted by SilverQuest’s customers (automotive companies) to secure their latest autonomous driving models, but also be commercialised as a toolset that can be plugged into existing autonomous vehicles to detect and prevent malicious attacks on autonomous driv ....A safety-preserving ecosystem for autonomous driving. In this project, Macquarie University will collaborate with UTS and SilverQuest to develop an innovative safety-preserving ecosystem for autonomous driving. This system will not only be adopted by SilverQuest’s customers (automotive companies) to secure their latest autonomous driving models, but also be commercialised as a toolset that can be plugged into existing autonomous vehicles to detect and prevent malicious attacks on autonomous driving models. The project will lead to two innovations: in theory design an attack detection and prevention ecosystem for autonomous driving and in application implement a safety analysis toolset for industry-scale autonomous systems.Read moreRead less
New real-time risk indicators to improve the efficiency, environmental impact and safety of air traffic management. Air-traffic demand is constantly rising, and Australia is responsible for the management of 11 per cent of the world's airspace. This project aims to develop risk indicators which will enable us to monitor air-safety risks on a constantly updated basis.
Classification and Prediction Modelling for Financial Distress, Tax Debt and Insolvency for ATO Clients. The Australian Taxation Office (ATO) has clients who are not able to meet their taxation debts, resulting in revenue shortfalls for both the State and Federal Governments. Through this project, we will develop predictive models and techniques which identify client classes and clusters in the ATO client population and the defining attributes of these collections - especially those which are a ....Classification and Prediction Modelling for Financial Distress, Tax Debt and Insolvency for ATO Clients. The Australian Taxation Office (ATO) has clients who are not able to meet their taxation debts, resulting in revenue shortfalls for both the State and Federal Governments. Through this project, we will develop predictive models and techniques which identify client classes and clusters in the ATO client population and the defining attributes of these collections - especially those which are at high risk of incurring debt and defaulting on paying taxes. In turn, the early identification of clients in financial distress will allow the ATO to give them assistance so that they can reduce their debts and meet their financial obligations.Read moreRead less
Intelligent Decision Support for Neonatal Analysis and Trend Detection. Nearly five percent of newborn babies require intensive care after birth. Several electronic instruments monitor a baby's vital signs such as blood oxygen, blood pressure and heart rate. A major limitation in neonatal clinical management is that the physiological data generated by the monitors is not extracted to provide an integrated picture of the baby's condition or to enable detection of trends and patterns in clinical a ....Intelligent Decision Support for Neonatal Analysis and Trend Detection. Nearly five percent of newborn babies require intensive care after birth. Several electronic instruments monitor a baby's vital signs such as blood oxygen, blood pressure and heart rate. A major limitation in neonatal clinical management is that the physiological data generated by the monitors is not extracted to provide an integrated picture of the baby's condition or to enable detection of trends and patterns in clinical and real-time physiological data. This project will develop a methodology and technology that supports neonatal analysis incorporating a framework to mine data for trend detection, resulting in higher survival rates.Read moreRead less
Intelligent Design Advisor for Manufacturing Process Knowledge within Concurrent Engineering in the Aerospace Industry. At present the design of engineering components in the aerospace industry is accomplished by experts from design and manufacturing either sequentially or in collaboration. If performed in sequence then time and quality is jeopardised. If performed in collaboration then more manpower than is necessary is expended. The aim of this project is to develop an intelligent design advis ....Intelligent Design Advisor for Manufacturing Process Knowledge within Concurrent Engineering in the Aerospace Industry. At present the design of engineering components in the aerospace industry is accomplished by experts from design and manufacturing either sequentially or in collaboration. If performed in sequence then time and quality is jeopardised. If performed in collaboration then more manpower than is necessary is expended. The aim of this project is to develop an intelligent design advisor for Manufacturing Process Knowledge that will provide this expert knowledge to the design engineer in order to speed up the design process while reducing costs and still maintaining the high standard of quality necessary in the Aerospace industry.Read moreRead less
High Frequency Data Stream Event Correlation for Complex Neonatal Medical Alerts. Nearly twenty percent of newborn babies require intensive care after birth. Several electronic instruments monitor a baby's vital signs such as blood oxygen, blood pressure and heart rate. A major limitation in neonatal clinical management is that the data generated by these monitors is not integrated to enable the alerting of condition deterioration or early warning of possible condition onset. This project will d ....High Frequency Data Stream Event Correlation for Complex Neonatal Medical Alerts. Nearly twenty percent of newborn babies require intensive care after birth. Several electronic instruments monitor a baby's vital signs such as blood oxygen, blood pressure and heart rate. A major limitation in neonatal clinical management is that the data generated by these monitors is not integrated to enable the alerting of condition deterioration or early warning of possible condition onset. This project will develop a methodology and technology that supports the cross correlation of neonatal clinical and physiological data for complex neonatal medical alerts, through the use of agents within an event stream processor, resulting in higher survival rates.Read moreRead less
Visual analytics for high volume multi attribute financial data streams. While our ability to accumulate data (such as financial data) is increasing, our capability to analyse them is still inadequate despite technological improvements. The new Visual Analytics methods will allow processing of the massive and time-varying data so that the time-critical decisions can be made with minimum effort.
Intelligent CRM through Conjoint Data Mining of Heterogeneous Sources. This project aims to investigate and develop techniques to improve customer relationship management (CRM) for public and private organisations. It aims to develop an intelligent framework to assist in adaptive marketing and management of customers. The framework is designed to manage multiple information resources for information sharing, and to synthesise knowledge through visualisation. Intended outcomes are standardised XM ....Intelligent CRM through Conjoint Data Mining of Heterogeneous Sources. This project aims to investigate and develop techniques to improve customer relationship management (CRM) for public and private organisations. It aims to develop an intelligent framework to assist in adaptive marketing and management of customers. The framework is designed to manage multiple information resources for information sharing, and to synthesise knowledge through visualisation. Intended outcomes are standardised XML profiles for the different data sets and business processes, novel techniques for conjoint mining of structured and semi-structured data, and adaptive business intelligence techniques. The results will be validated using large real-world data sets provided by the partner organisation.Read moreRead less
Scenario driven management in a network environment. Scenario planning is the process of identifying plausible futures and their inherent risks. The organisation, the network within which it is embedded, and the environment in which the network operates, form a complex system of non-linear, dynamic, interrelationships. This project will develop a continuous process of scenario planning, capturing learning about the future as it emerges. The project fuses the use of agents for intelligent data co ....Scenario driven management in a network environment. Scenario planning is the process of identifying plausible futures and their inherent risks. The organisation, the network within which it is embedded, and the environment in which the network operates, form a complex system of non-linear, dynamic, interrelationships. This project will develop a continuous process of scenario planning, capturing learning about the future as it emerges. The project fuses the use of agents for intelligent data collection and negotiation with agent-based modelling to build powerful network-based scenario modelling systems for commercial applications. This outcome will place Australia on the frontier of smart information use.Read moreRead less
Transfer Learning for Genome Analysis and Personalised Recommendation. This project aims to improve the accuracy, adaptability, and comprehensiveness of health characteristic predictions and provide personalised recommendations for healthcare service and disease prevention. The deliverables include uncertainty learning and multi-source transfer learning methodologies for predictions based on genome analysis that distils and transfers useful knowledge from multiple sources into an Australian geno ....Transfer Learning for Genome Analysis and Personalised Recommendation. This project aims to improve the accuracy, adaptability, and comprehensiveness of health characteristic predictions and provide personalised recommendations for healthcare service and disease prevention. The deliverables include uncertainty learning and multi-source transfer learning methodologies for predictions based on genome analysis that distils and transfers useful knowledge from multiple sources into an Australian genome analysis model. A federated cross-domain recommender system will be developed to profile individuals and generate personalised recommendations. The outcomes are expected to create a paradigm shift in learning-based prediction and personalised recommendations to support healthcare services in complex environments. Read moreRead less