Real-time and self-adaptive stream data analyser for intensive care management. The clinical benefit of this project will be in improved success rates and reduced mortality and risk in surgery and intensive care units. The Information and communication technology (ICT) benefit of this project is associated with the novel online algorithms and models aligned with the stream data research, and will be enhanced by our stream compression techniques. The stream data analyser developed in this projec ....Real-time and self-adaptive stream data analyser for intensive care management. The clinical benefit of this project will be in improved success rates and reduced mortality and risk in surgery and intensive care units. The Information and communication technology (ICT) benefit of this project is associated with the novel online algorithms and models aligned with the stream data research, and will be enhanced by our stream compression techniques. The stream data analyser developed in this project will be suitable for more than medical surveillance data; it will also improve the processing of other kinds of massive stream data (for example data from remote sensors, communication networks and other dynamic environments). The project involves a scientifically rich collaboration that will enhance the skills of PhD students and staff and drive the field forward.Read moreRead less
The right to be forgotten: GDPR modelling in cross-domain social networks . The project aims to develop a theoretical model and practical mechanisms to address the critical challenge – ‘right to be forgotten’ - raised from the General Data Protection Regulation (GDPR) with minimal compromising of the utility of the data. To achieve the aim, we will design a ‘right to be forgotten’ framework and associated erasure mechanisms that are effective even information is derived from multiple related soc ....The right to be forgotten: GDPR modelling in cross-domain social networks . The project aims to develop a theoretical model and practical mechanisms to address the critical challenge – ‘right to be forgotten’ - raised from the General Data Protection Regulation (GDPR) with minimal compromising of the utility of the data. To achieve the aim, we will design a ‘right to be forgotten’ framework and associated erasure mechanisms that are effective even information is derived from multiple related social networks. The framework will be created by identifying heterogeneous information, modelling individual behaviour patterns and designing erasure policies. The outcomes of the project can be used by the government to provide privacy guarantees to Australian cyberspace and by industry to protect their clients’ privacy.Read moreRead less
Enhancing privacy preserving in dynamic cyberspace. This project aims to develop a novel infrastructure operational monitoring and management strategy to reduce the redundant maintenance actions and achieve a cost-effective approach for civil infrastructure asset management. The project will use multiple social networks as a platform for the project, with the potential for the results to be extended to any dynamic cyberspace. Project outcomes will include a set of new analysis theories and tools ....Enhancing privacy preserving in dynamic cyberspace. This project aims to develop a novel infrastructure operational monitoring and management strategy to reduce the redundant maintenance actions and achieve a cost-effective approach for civil infrastructure asset management. The project will use multiple social networks as a platform for the project, with the potential for the results to be extended to any dynamic cyberspace. Project outcomes will include a set of new analysis theories and tools to facilitate government, companies, individuals, and organisations to enhance their information gathering and privacy-preserving capabilities. This is expected to enhance the credibility of the government and organisations and save the possible financial loss of companies and individuals.Read moreRead less
Privacy preservation for personalised smart devices. The goal of this project is to build a privacy preservation framework for personalised smart devices with both immediate and long-term applications in a range of industries. The novel theoretical contributions include a privacy-preservation mechanism that guards against attacks by intelligent tools, a model and metrics that distinguish between object detection and object recognition, and allowing users to specify their desired level of privacy ....Privacy preservation for personalised smart devices. The goal of this project is to build a privacy preservation framework for personalised smart devices with both immediate and long-term applications in a range of industries. The novel theoretical contributions include a privacy-preservation mechanism that guards against attacks by intelligent tools, a model and metrics that distinguish between object detection and object recognition, and allowing users to specify their desired level of privacy guarantee. Practically, these solutions have clear economic and public-safety benefits. The solutions will accelerate AI device development, advance smart technologies based on individual behaviours, and guarantee personal data privacy against both human attackers and adversarial algorithms. Read moreRead less
Blockchain-Enabled Federated Learning for Secure and Decentralised Learning. This project aims to develop novel blockchain-enabled federated learning techniques for secure and decentralised learning. It addresses an important and urgent machine learning problem, that is, the data useful for training machine learning models are often held by different owners who are not willing to share their data due to privacy concerns, resulting in isolated data islands. The project will result in a set of inn ....Blockchain-Enabled Federated Learning for Secure and Decentralised Learning. This project aims to develop novel blockchain-enabled federated learning techniques for secure and decentralised learning. It addresses an important and urgent machine learning problem, that is, the data useful for training machine learning models are often held by different owners who are not willing to share their data due to privacy concerns, resulting in isolated data islands. The project will result in a set of innovative algorithms that provide solutions to the key challenges in blockchain-enabled federated learning. The expected outcomes of the project will dramatically advance the frontier of machine learning and blockchain research, and have massive social and economic benefits for Australia and international communities.Read moreRead less
Next-generation Intelligent Explorations of Geo-located Data . This project aims to build a next-generation intelligent exploration framework over massive geo-located data, varying from points-of-interest to areas-of-interest data, in order to dramatically enhance user experiences when interacting with various forms of geo-located data over maps. Expected outcomes include novel exploration models, efficient and scalable algorithms for retrieving and visualizing the exploration results, online up ....Next-generation Intelligent Explorations of Geo-located Data . This project aims to build a next-generation intelligent exploration framework over massive geo-located data, varying from points-of-interest to areas-of-interest data, in order to dramatically enhance user experiences when interacting with various forms of geo-located data over maps. Expected outcomes include novel exploration models, efficient and scalable algorithms for retrieving and visualizing the exploration results, online updating of personal preferences during the life cycle of exploration, as well as a prototype system to evaluate and demonstrate practical value of the research. It will complement existing map services and significantly benefit many location-aware services, e.g., logistics, health services and urban planning.Read moreRead less
Enhancing information credibility using mathematical prediction. The aim of this project is to develop theory, techniques, mathematical tools and practical algorithms for rumor detection and forecast in social media to enhance credibility of news, especially in time-sensitive situations and trending events. This project will significantly advance human knowledge of rumor formation, detection, and forecast, which will enable timely and efficient counter attacks. The outcomes from this project wil ....Enhancing information credibility using mathematical prediction. The aim of this project is to develop theory, techniques, mathematical tools and practical algorithms for rumor detection and forecast in social media to enhance credibility of news, especially in time-sensitive situations and trending events. This project will significantly advance human knowledge of rumor formation, detection, and forecast, which will enable timely and efficient counter attacks. The outcomes from this project will offer a reliable information environment for our society.Read moreRead less
QualA-D: a quality aware query engine for next generation data integration systems. This project will address the growing diversity of the web/user community by developing new approaches for data integration that incorporate data quality requirements such as data currency, completeness and coverage. First-of-breed quality aware query system is expected to be developed that will assist in improving user experience and satisfaction.
Discovery Early Career Researcher Award - Grant ID: DE140100215
Funder
Australian Research Council
Funding Amount
$394,752.00
Summary
Searching Activity Trajectories for Intention Oriented Recommendations. The ubiquitous fusion of social network services and Global Positioning System-enabled mobile devices has generated large-scale activity trajectory data representing the footprint of people's daily activities. It presents an unprecedented opportunity to build highly intelligent recommendation systems. Existing approaches that merely focus on the location aspect of trajectories are limited in their ability to understand genui ....Searching Activity Trajectories for Intention Oriented Recommendations. The ubiquitous fusion of social network services and Global Positioning System-enabled mobile devices has generated large-scale activity trajectory data representing the footprint of people's daily activities. It presents an unprecedented opportunity to build highly intelligent recommendation systems. Existing approaches that merely focus on the location aspect of trajectories are limited in their ability to understand genuine preferences from travel histories, due to lack of consideration for activity information as well as the associated semantics and context. This project aims to address these issues and provide effective recommendations by considering both users’ intention and collective behavioural knowledge inferred from activity trajectories.Read moreRead less
Real-time Event Detection, Prediction, and Visualization for Emergency Response. This project proposes novel end-to-end methods for real-time recognition and prediction of real-world events, leading to timely response to emergencies such as disease outbreaks and natural disasters, as well as prevention of crime, security breaches and the like. It will develop new techniques to quickly detect and predict events by incorporating adaptive learning and probabilistic models, and address fusion and sc ....Real-time Event Detection, Prediction, and Visualization for Emergency Response. This project proposes novel end-to-end methods for real-time recognition and prediction of real-world events, leading to timely response to emergencies such as disease outbreaks and natural disasters, as well as prevention of crime, security breaches and the like. It will develop new techniques to quickly detect and predict events by incorporating adaptive learning and probabilistic models, and address fusion and scalability factors to handle vast collections of heterogeneous data. An event surveillance system prototype will be developed to incorporate the findings of the research with tools to visualise and describe events.Read moreRead less