Learning Semi-Naive Bayesian Classifiers from Numeric Data. This project addresses research priority 3, offering frontier technologies. It will deliver better and faster classification technologies that greatly help accomplish many real-world tasks including medical diagnosis, fraud detection, spam filtering and webpage search, where accurate and fast classification is critical to save life, increase efficiency, reduce crime and conserve resources. Hence this project addresses priority 4 as well ....Learning Semi-Naive Bayesian Classifiers from Numeric Data. This project addresses research priority 3, offering frontier technologies. It will deliver better and faster classification technologies that greatly help accomplish many real-world tasks including medical diagnosis, fraud detection, spam filtering and webpage search, where accurate and fast classification is critical to save life, increase efficiency, reduce crime and conserve resources. Hence this project addresses priority 4 as well, better safeguarding Australia from disease and crime. This project will also support a young research group of international standing. It will train the involved researchers to attain a high level of proficiency and excellence in machine learning research and development.Read moreRead less
Investigation and development of robust rule discovery and classification system. This research focuses on a national research priority, namely smart information use. The expected outcomes of the project will greatly advance intelligent system design, such as automatic decision making, fault detection and problem diagnosis, for finance, medical, telecom and many other areas. It has great potential for commercialisation and earning incomes for the future research. The publications will benefit th ....Investigation and development of robust rule discovery and classification system. This research focuses on a national research priority, namely smart information use. The expected outcomes of the project will greatly advance intelligent system design, such as automatic decision making, fault detection and problem diagnosis, for finance, medical, telecom and many other areas. It has great potential for commercialisation and earning incomes for the future research. The publications will benefit the future development of intelligent systems for dealing with missing data. This project directly supports a PhD student and two research assistants who will most likely continue their higher degree study. These contribute to regional tertiary education.Read moreRead less
Discovering justified knowledge from data. Knowledge discovery from data has assumed a critical role in numerous areas of science, commerce and public administration. However, its effectiveness is limited by the undesirable propensity of current techniques to make many false, as well as real, discoveries. This research will rectify that problem, a critical outcome given the potential cost of making decisions or setting policy using flawed information. For example, it may prevent the adoption of ....Discovering justified knowledge from data. Knowledge discovery from data has assumed a critical role in numerous areas of science, commerce and public administration. However, its effectiveness is limited by the undesirable propensity of current techniques to make many false, as well as real, discoveries. This research will rectify that problem, a critical outcome given the potential cost of making decisions or setting policy using flawed information. For example, it may prevent the adoption of ineffective strategies for addressing land degradation; inappropriately targeted public health expenditure; expensive development and clinical trialing of drugs which prove ineffective; and wasted police and security investigations into unfounded suspicions of criminal or terrorist activity.Read moreRead less
Fuzzy Transfer Learning for Prediction in Data-Shortage and Rapidly-Changing Environments. Collecting sufficient up-to-date data to train a learning model for data analysis and prediction is difficult and expensive. This project will develop a Fuzzy Transfer Learning methodology, using Information Granularity theory, that exploits data with different features and/or distributions available in other, similar systems, to provide accurate learning-based prediction for current problems. It will esta ....Fuzzy Transfer Learning for Prediction in Data-Shortage and Rapidly-Changing Environments. Collecting sufficient up-to-date data to train a learning model for data analysis and prediction is difficult and expensive. This project will develop a Fuzzy Transfer Learning methodology, using Information Granularity theory, that exploits data with different features and/or distributions available in other, similar systems, to provide accurate learning-based prediction for current problems. It will establish a new research direction, Fuzzy Transfer Learning for Prediction, and the outcomes will enable government and industry to better use past experience to make more accurate predictions and decisions. Highly significant benefits will also accrue in the data analytics, business intelligence and decision making research fields.Read moreRead less
Improving human reasoning with causal Bayes networks: a multimodal approach. This project aims to improve human causal and probabilistic reasoning about complex systems by taking a user-centric, multimodal, interactive approach. The project will explore new integrated visual and verbal ways of explaining a causal probabilistic model and its reasoning, to reduce known human reasoning difficulties, and investigate how to reduce cognitive load by prioritising the most useful user- and context-speci ....Improving human reasoning with causal Bayes networks: a multimodal approach. This project aims to improve human causal and probabilistic reasoning about complex systems by taking a user-centric, multimodal, interactive approach. The project will explore new integrated visual and verbal ways of explaining a causal probabilistic model and its reasoning, to reduce known human reasoning difficulties, and investigate how to reduce cognitive load by prioritising the most useful user- and context-specific information. Expected outcomes include novel AI methods that empower users to drive the reasoning process and strengthen trust in the system’s reasoning. Performance will be assessed in medical and legal domains, with significant potential benefits to end users from better, more transparent reasoning and decision making.Read moreRead less
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
Optimizing steel industry supply chains through constraint and market-oriented programming. Supply chain optimization is a difficult problem, but of considerable significance to business enterprises. Constraint programming technology is a promising approach to solving such problems, but is inadequate in the context of dynamic supply chains. Market-oriented programming solves resource allocation problems by setting up artificial computational economies of trading software agents and holds promise ....Optimizing steel industry supply chains through constraint and market-oriented programming. Supply chain optimization is a difficult problem, but of considerable significance to business enterprises. Constraint programming technology is a promising approach to solving such problems, but is inadequate in the context of dynamic supply chains. Market-oriented programming solves resource allocation problems by setting up artificial computational economies of trading software agents and holds promise both as an optimization tool and as a tool that supports explicit market negotiation. This project seeks to address several open questions relating to the integrated deployment of these two classes of techniques, in the context of building a practical supply chain optimization system for BHP Steel.Read moreRead less
Intelligently Activated Sensor Clusters for E-Commerce Applications. This project will investigate intelligent management of large sensor clusters installed in mechanical structures for use in Electronic Commerce applications. Finding algorithms for optimised placement of remotely controlled power supply and the communication unit in each sensor cluster is the first aim. Development of a sensor management algorithm that process user inputs submitted through the Internet and that exploits past se ....Intelligently Activated Sensor Clusters for E-Commerce Applications. This project will investigate intelligent management of large sensor clusters installed in mechanical structures for use in Electronic Commerce applications. Finding algorithms for optimised placement of remotely controlled power supply and the communication unit in each sensor cluster is the first aim. Development of a sensor management algorithm that process user inputs submitted through the Internet and that exploits past sensor data is the second aim. Since there is no such system available in the market, the project will have strong impacts in E-Commerce applications and bridge instrumentation systems useful to a wider community also advancing the research in clustering and expert systems.Read moreRead less
A generic decision-making design environment to enable end users in rural industries to develop expert systems. Successful decision support systems developed by end-users has been limited: our proposed approach advances this capability. Using natural representations of industry knowledge, this project will specify a generic design environment in which industry end-users can develop relevant decision support systems. It extends expert systems technologies to overcome known limitations, increasin ....A generic decision-making design environment to enable end users in rural industries to develop expert systems. Successful decision support systems developed by end-users has been limited: our proposed approach advances this capability. Using natural representations of industry knowledge, this project will specify a generic design environment in which industry end-users can develop relevant decision support systems. It extends expert systems technologies to overcome known limitations, increasing context and relevance and encouraging user uptake. Key industry stakeholders will select relevant problems to identify decision categories, leading to specification of the generic design environment. This promises improved decision quality for dairy farmers in the recently deregulated dairy industry; the design environment will be transferable to other rural industries.Read moreRead less
Intelligent Structured Knowledge Source Integration via Software Agents. This project aims to use flexible information agents to integrate the World Wide Web with a machine readable ontology, namely a large, consistent collection of common sense knowledge. The best developed ontology in the world is Cyc. Cyc's repository of general purpose knowledge is rich and stable, but has a major limitation in requiring its knowledge to be hand-entered by experts. The outcomes of the project will be increas ....Intelligent Structured Knowledge Source Integration via Software Agents. This project aims to use flexible information agents to integrate the World Wide Web with a machine readable ontology, namely a large, consistent collection of common sense knowledge. The best developed ontology in the world is Cyc. Cyc's repository of general purpose knowledge is rich and stable, but has a major limitation in requiring its knowledge to be hand-entered by experts. The outcomes of the project will be increased functionality for ontologies, to enable expert reasoning programs wishing to use a formal ontology such as Cyc to have access to the wealth of knowledge on the World Wide Web.Read moreRead less