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
Formalising and automating the elicitation and reconciliation of requirements from multiple stakeholders. It is well recognised that requirements specifications are often error-prone and that it is much cheaper to detect and fix these errors early in the software development life cycle than later. A major problem with requirements determination is that each and every stakeholder has his/her own representation of the enterprise reality. This project seeks to take these views and use set-theore ....Formalising and automating the elicitation and reconciliation of requirements from multiple stakeholders. It is well recognised that requirements specifications are often error-prone and that it is much cheaper to detect and fix these errors early in the software development life cycle than later. A major problem with requirements determination is that each and every stakeholder has his/her own representation of the enterprise reality. This project seeks to take these views and use set-theoretical techniques from Formal Concept Analysis (FCA) to automatically generate and compare the underlying conceptual models. A process model based on FCA has been proposed which we will extend and empirically evaluate in this project. The result will be a more rigorous and yet pragmatic approach to requirements engineering which offers the greatest economic leverage.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
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
A more intelligent knowledge-based system apprentice. Our previous techniques already had an impact on Australian industry, with five Australian companies marketing such technology, and for three of these it is a central technology. We expect an early uptake of the enhancements we propose by these companies, greatly increasing their international competitiveness against other rule technologies. Three of these companies are very recent, so we would expect other company uptake of the new enhance ....A more intelligent knowledge-based system apprentice. Our previous techniques already had an impact on Australian industry, with five Australian companies marketing such technology, and for three of these it is a central technology. We expect an early uptake of the enhancements we propose by these companies, greatly increasing their international competitiveness against other rule technologies. Three of these companies are very recent, so we would expect other company uptake of the new enhanced technology. In turn Australian companies using the technology will improve their competitiveness in an increasingly knowledge-based economy by being able to more rapidly and easily deploy knowledge-based systems. Our previous techniques have already had a significant impact in medical practice.Read moreRead less
Integrated constraint-based planning and scheduling. Constraint programming is a relatively new technology based on artificial intellgence techniques that is becoming a popular tool for developing industrial optimisation solutions. While constraint programming has been used extensively for solving industrial scheduling problems, very little has been done in developing constraint-based integrated producting planning and scheduling systems. The size and complexity of typical production planning a ....Integrated constraint-based planning and scheduling. Constraint programming is a relatively new technology based on artificial intellgence techniques that is becoming a popular tool for developing industrial optimisation solutions. While constraint programming has been used extensively for solving industrial scheduling problems, very little has been done in developing constraint-based integrated producting planning and scheduling systems. The size and complexity of typical production planning and scheduling problems requires the innovative use of the latest developments in constraint programming technology, together with a variety of other artificial intelligence techniques. This project seeks to develop and implement a new conceptual framework for integrated constraint-based planning and scheduling, using BHP Steel as a test - bed.Read moreRead less
Mining Distributed, High-Speed, Time-Variant Data Streams. With the high-speed and large volume of data generation, the data mining research community is facing an unprecedented challenge to provide instant data mining outcomes for prompt usage. Getting access to derived information from multiple, dynamically changing data is vital for many business, science and security services. Extended networks of sensors and other devices assist many environments with data collection that should be correlat ....Mining Distributed, High-Speed, Time-Variant Data Streams. With the high-speed and large volume of data generation, the data mining research community is facing an unprecedented challenge to provide instant data mining outcomes for prompt usage. Getting access to derived information from multiple, dynamically changing data is vital for many business, science and security services. Extended networks of sensors and other devices assist many environments with data collection that should be correlated and processed towards discovery of dependencies, regularities and patterns. Data mining tools, especially of this new generation, are capable of dealing with data streams, and they offer great benefits for users from many industry sectors; defence, health management, security, commerce and science.Read moreRead less
Next Generation Grid Enabled Cluster Computers: Performance Optimisation for e-Science. In partnership with a local computer company this project will develop cost effective cluster computing solutions assembled from off-the-shelf parts for $50,000-$200,000. This price range is currently relatively poorly serviced by the multinational computer vendors, who tend to focus on the high density compute systems necessary for very large cluster systems. As a consequence the development of high performa ....Next Generation Grid Enabled Cluster Computers: Performance Optimisation for e-Science. In partnership with a local computer company this project will develop cost effective cluster computing solutions assembled from off-the-shelf parts for $50,000-$200,000. This price range is currently relatively poorly serviced by the multinational computer vendors, who tend to focus on the high density compute systems necessary for very large cluster systems. As a consequence the development of high performance computing in Australia has been somewhat stifled compared to the US or UK, where there exist small niche companies servicing this market sector. This project aims to change this, developing affordable high performance cluster computing systems for the Australian market place and beyond.Read moreRead less
Extending association rule discovery to numeric data. This project tackles a key limitation of association-rule discovery, which is one of the main techniques used in data mining. Much valuable data is numeric. However, association-rule discovery cannot satisfactorily model numeric data, a limitation that has greatly restricted its application. This project investigates a novel new technique that overcomes this limitation. Impact-rule discovery finds associations with numeric distributions. ....Extending association rule discovery to numeric data. This project tackles a key limitation of association-rule discovery, which is one of the main techniques used in data mining. Much valuable data is numeric. However, association-rule discovery cannot satisfactorily model numeric data, a limitation that has greatly restricted its application. This project investigates a novel new technique that overcomes this limitation. Impact-rule discovery finds associations with numeric distributions. This allows data analysts to discover precisely the type of information that they usually seek from numeric data, for example, how to maximize either average or aggregate measures of outcomes such as health, compliance, profit, or accuracy.Read moreRead less