A painless approach to support efficient querying and mining of spatial data through smart transformations. This project will develop spatial data retrieval methods that are not only highly efficient but also easy to implement ('painless'). It will help businesses such as digital map providers, location based service providers and medical researchers quickly possess this key enabling technique for their large scale spatial querying and mining needs.
From Data to Artefact: a Key Ingredient in Service Interoperation. Supporting service interoperation in the e-Business environment is crucial in automating business transactions across organisation boundaries. If no proper mechanism is in place, business delays, failures, and serious disputes can occur. This project will explore new avenues to this long-standing and challenging problem by providing an artefact framework to model and manage business collaboration. Given this project's unique pers ....From Data to Artefact: a Key Ingredient in Service Interoperation. Supporting service interoperation in the e-Business environment is crucial in automating business transactions across organisation boundaries. If no proper mechanism is in place, business delays, failures, and serious disputes can occur. This project will explore new avenues to this long-standing and challenging problem by providing an artefact framework to model and manage business collaboration. Given this project's unique perspective and approaches that are directly applicable to existing enterprise systems, there is a strong potential for its results to lead to a new generation of e-Business design and management, advance the knowledge base of the discipline and yield high returns to the Australian service society and IT industry.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210101458
Funder
Australian Research Council
Funding Amount
$387,141.00
Summary
Scalable and Deep Anomaly Detection from Big Data with Similarity Hashing. Anomaly detection, aiming to identify anomalous but insightful patterns in data mining, is an important big data analytics technique. The nature of big data requires a detection method that can handle fast-evolving data of diverse types. However, existing methods suffer from either high computational cost or low detection performance. This project aims to develop a detection framework to advance detection performance and ....Scalable and Deep Anomaly Detection from Big Data with Similarity Hashing. Anomaly detection, aiming to identify anomalous but insightful patterns in data mining, is an important big data analytics technique. The nature of big data requires a detection method that can handle fast-evolving data of diverse types. However, existing methods suffer from either high computational cost or low detection performance. This project aims to develop a detection framework to advance detection performance and efficiency, based on a novel deep learning model called deep isolation forest which is different from the traditional artificial neural network based models. The outcome will bring huge benefits to various applications such as real-time predictive maintenance in smart manufacturing, and intrusion detection in cybersecurity.Read moreRead less
Big data fast response: real-time classification of big data stream. This project will provide a big data stream based data mining framework to build a real-time monitoring and decision making platform for business and government big data. By clever use of smart information, this breakthrough science will provide frontier technologies for managing and using huge data for social and economic benefits globally.
Enabling User-Centric Wisdom Engines for Big Information Network Search. Big information networks, for example social networks, are important for modern information systems, yet searching for useful information from huge networks is difficult because network structure and user relationships continuously evolve. This project will provide theoretical foundations for structural knowledge mining to enable user-centric wisdom search on big information networks. Expected outcomes are: real-world appli ....Enabling User-Centric Wisdom Engines for Big Information Network Search. Big information networks, for example social networks, are important for modern information systems, yet searching for useful information from huge networks is difficult because network structure and user relationships continuously evolve. This project will provide theoretical foundations for structural knowledge mining to enable user-centric wisdom search on big information networks. Expected outcomes are: real-world application platform to support information network analysis; theories for big network control, algorithms, and systematic solutions to enable user-centric knowledge search, including a new search engine for big information networks. By significantly improving IT, it will benefit Australian business, industry and the wider community.Read moreRead less
Privacy Preserving Data Sharing in Electronic Health Environment. This project aims to improve access to electronic health data (EHD) while still ensuring patient privacy. EHD can provide important information for medical research and health-care resource allocations. However, data sharing in electronic health environments is challenging because of the privacy concerns of customers. Large-scale unauthorised access from internal staff has been reported in Medicare. This project aims to develop ne ....Privacy Preserving Data Sharing in Electronic Health Environment. This project aims to improve access to electronic health data (EHD) while still ensuring patient privacy. EHD can provide important information for medical research and health-care resource allocations. However, data sharing in electronic health environments is challenging because of the privacy concerns of customers. Large-scale unauthorised access from internal staff has been reported in Medicare. This project aims to develop new privacy-preserving algorithms on EHD database federations, which can provide efficient data access yet block inside attacks. It will significantly improve the data available for medical research, while reducing the cost of EHD system management and providing visualised decision supports to medical staff and the government health resource planners.Read moreRead less
Transaction Oriented Computational Models for Multi Agent Systems. Agent systems are a very promising technology for constructing complex, large-scale software. Australian researchers have made key
contributions in this area, particularly with reference to one mature and commonly adopted agent architecture known as BDI (Belief, Desire, Intention). To make this technology suitable for use in advanced applications, it has to be provided with robust and predictable behaviour. This project wil ....Transaction Oriented Computational Models for Multi Agent Systems. Agent systems are a very promising technology for constructing complex, large-scale software. Australian researchers have made key
contributions in this area, particularly with reference to one mature and commonly adopted agent architecture known as BDI (Belief, Desire, Intention). To make this technology suitable for use in advanced applications, it has to be provided with robust and predictable behaviour. This project will address that need by designing and implementing a novel agent language for BDI, based on contributions using transactional concepts for agents developed at The University of Melbourne. This will contribute to the development of robust and predictable agent software, that can be used in complex and large scale applications of the future.
Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE140100387
Funder
Australian Research Council
Funding Amount
$349,179.00
Summary
Mining Patterns and Changes of Wave Shapes for Efficiently Querying Periodic Data Streams. Many data streams change periodically, such as vital physiological parameters (for example, heart rate, arterial pressure and respiratory impedance) and seasonal environmental data streams (for example, temperature and turbidity of river water). However, the querying of periodic data streams faces great challenges, including the issue of critical signals being generally buried within massive data while cri ....Mining Patterns and Changes of Wave Shapes for Efficiently Querying Periodic Data Streams. Many data streams change periodically, such as vital physiological parameters (for example, heart rate, arterial pressure and respiratory impedance) and seasonal environmental data streams (for example, temperature and turbidity of river water). However, the querying of periodic data streams faces great challenges, including the issue of critical signals being generally buried within massive data while critical changes between similar wave shapes are difficult to recognise due to shifting, scaling and noise. This project will develop new mining algorithms to resolve these challenges by segmenting periodic wave shapes, discovering shape patterns and shape changes, and summarising raw data streams so that the summarised data can directly answer various user queries for efficiency.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE130100911
Funder
Australian Research Council
Funding Amount
$339,434.00
Summary
Accurate and online abnormality detection in multiple correlated time series. This study will develop a new kernel-based and online support vector regression method for real-time and correlated multiple time series and promote their use in critical applications, which will save money and lives. Examples include the detection of stock market crisis events and detection of patients' condition deterioration in the operating theatre.
Investigation and Development of Parallel Large Scale Record Linkage Techniques. Record linkage aims at matching records of the same entity (like customer or patient) in large (administrative) databases. The outcomes of the proposed research will improve current techniques in terms of efficiency, accuracy and the need for human intervention. Through experimental studies and stochastic modelling the performance of traditional and new methods for data cleaning, standardisation and linkage will be ....Investigation and Development of Parallel Large Scale Record Linkage Techniques. Record linkage aims at matching records of the same entity (like customer or patient) in large (administrative) databases. The outcomes of the proposed research will improve current techniques in terms of efficiency, accuracy and the need for human intervention. Through experimental studies and stochastic modelling the performance of traditional and new methods for data cleaning, standardisation and linkage will be assessed. The effect of the statistical dependency of attribute values will be studied. New methods using clustering for blocking large datasets, and predictive models including interaction terms will be implemented, analysed and evaluated on high-performance computers and office-based PC clusters.
Read moreRead less