Smart micro learning with open education resources. This project aims to enhance personalised learning systems for mobile device users . Open online education is gaining in popularity with its ease of use. The project tackles the problems in relation to more and more popular mobile and ‘micro learning’, where people learn on the move and within small units of time. Ontology and machine learning technologies used in this project will help to optimise the offering of open education resources, by p ....Smart micro learning with open education resources. This project aims to enhance personalised learning systems for mobile device users . Open online education is gaining in popularity with its ease of use. The project tackles the problems in relation to more and more popular mobile and ‘micro learning’, where people learn on the move and within small units of time. Ontology and machine learning technologies used in this project will help to optimise the offering of open education resources, by providing solutions meeting each individual learner’s needs. The main outcome will consolidate a cloud based micro learning framework through integrating a group of novel algorithms.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210100274
Funder
Australian Research Council
Funding Amount
$415,675.00
Summary
Graph Neural Networks for Efficient Decision-making towards Future Grids. This project aims to develop a breakthrough framework for decision-focused learning by integrating explainable graph neural networks and efficient computational methods. It expects to create new methodologies of graph representation learning for unlocking data insight with spatiotemporal knowledge while to build new accelerated optimisation theories for speeding up decision-focused learning model. The expected outcomes wil ....Graph Neural Networks for Efficient Decision-making towards Future Grids. This project aims to develop a breakthrough framework for decision-focused learning by integrating explainable graph neural networks and efficient computational methods. It expects to create new methodologies of graph representation learning for unlocking data insight with spatiotemporal knowledge while to build new accelerated optimisation theories for speeding up decision-focused learning model. The expected outcomes will advance big spatiotemporal data analytics and nonlinear optimisation theory for solving decision-making tasks towards a future energy system. This should promote the Australian power industry transition to a sustainable future grid based on a digitalisation approach to efficient energy management against climate changes.Read moreRead less
Effective and Efficient Situation Awareness in Big Social Media Data . Crisis management services using traditional methods like phone calls can be easily delayed due to limited communication ability in the disaster area. This project aims to help users make smart decision in critical situations by using big social media data to detect complex social events, receive recommendations, and observe event summaries. We will invent advanced social data models, efficient indices and query techniques fo ....Effective and Efficient Situation Awareness in Big Social Media Data . Crisis management services using traditional methods like phone calls can be easily delayed due to limited communication ability in the disaster area. This project aims to help users make smart decision in critical situations by using big social media data to detect complex social events, receive recommendations, and observe event summaries. We will invent advanced social data models, efficient indices and query techniques for situation awareness in big media. We expect to develop a system to evaluate the proposed situation awareness framework. The outcomes of the project will benefit social media analysis and big data fields. It will also improve the government services by enabling the real time situation awareness in crisis.Read moreRead less
Increasing data quality with group associations in outsourcing environments. Outsourcing of data storage is increasingly common, but poses major problems for data utility and confidentiality. This project aims to discover how tuples (data structures) in fragments can be grouped to increase the utility of queries executed over fragments. The project will create a framework that satisfies information protection goals while achieving utility for queries. The developed algorithms and techniques will ....Increasing data quality with group associations in outsourcing environments. Outsourcing of data storage is increasingly common, but poses major problems for data utility and confidentiality. This project aims to discover how tuples (data structures) in fragments can be grouped to increase the utility of queries executed over fragments. The project will create a framework that satisfies information protection goals while achieving utility for queries. The developed algorithms and techniques will formally specify and develop a model to validate loose association rules while minimising data leakage risks. The outcomes will benefit Australians through enabling sharing and linking increasingly large datasets securely and cheaply.Read moreRead less
Data mining complex transactional and criminal networks. Money laundering, if undetected, poses a major concern for governments and communities. The software system platform for detecting money laundering networks from this project will be the first that can assist intelligence data analysts to detect unknown money laundering networks faster and more accurately, helping fight crimes more efficiently.
Effective Recommendations based on Multi-Source Data. Large-scale data collected from multiple sources such as the Web, sensor networks, academic publications, and social networks provide a new opportunity to exploit useful information for effective and efficient recommendations and decision making. The project will propose a new framework of recommender systems that is based on analysing relationships between different types of objects from multiple data sources. A graph model will be built to ....Effective Recommendations based on Multi-Source Data. Large-scale data collected from multiple sources such as the Web, sensor networks, academic publications, and social networks provide a new opportunity to exploit useful information for effective and efficient recommendations and decision making. The project will propose a new framework of recommender systems that is based on analysing relationships between different types of objects from multiple data sources. A graph model will be built to represent the extracted semantic relationships and novel linkage-analysis based algorithms will be developed for ranking objects. The results from this project will underpin many critical applications such as healthcare.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101310
Funder
Australian Research Council
Funding Amount
$426,918.00
Summary
Dimension-reduced Reinforcement Learning for Large-scale Fleet Management. This project aims to address the problems in large-scale fleet management to ensure the efficiency of tomorrow’s transportation models, such as on-demand ride-hailing and mobility-as-a-service. The expected outcomes of this project include improved techniques for optimising the utility of large fleets of vehicles, and particularly robust dimension-reduced reinforcement learning algorithms that are capable of handling the ....Dimension-reduced Reinforcement Learning for Large-scale Fleet Management. This project aims to address the problems in large-scale fleet management to ensure the efficiency of tomorrow’s transportation models, such as on-demand ride-hailing and mobility-as-a-service. The expected outcomes of this project include improved techniques for optimising the utility of large fleets of vehicles, and particularly robust dimension-reduced reinforcement learning algorithms that are capable of handling the complex dynamics of supply and demand in transportation. The results should advance both research and technology in academia and the transportation industry and will also provide significant benefits to Australia and the international community by enhancing the energy-efficiency of and access to the mobility of the future.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101610
Funder
Australian Research Council
Funding Amount
$403,398.00
Summary
Towards Explainable Multi-source Multivariate Time-series Analysis. The aim of this project is to build deep learning models with transparent reasoning behind the results that can be easily interpreted by humans. The research rests on translating pertinent knowledge from multiple sources of complex data containing event sequences into graph form and embedding those knowledge graphs into a sophisticated deep learning model. Such an accomplishment represents the next great advance in machine intel ....Towards Explainable Multi-source Multivariate Time-series Analysis. The aim of this project is to build deep learning models with transparent reasoning behind the results that can be easily interpreted by humans. The research rests on translating pertinent knowledge from multiple sources of complex data containing event sequences into graph form and embedding those knowledge graphs into a sophisticated deep learning model. Such an accomplishment represents the next great advance in machine intelligence and will lay the theoretical foundations for building intelligent analysis tools that truly work in tandem with people. The potential benefits to science, society, and the Australian economy, particularly in finance, sensor technologies, and emergency health services would be appreciable.Read moreRead less
Deep Pattern Mining for Dynamic Real-time Enterprise Scale Pricing. This project aims to build a pricing framework, based on deep pattern mining, to enable dynamic real-time pricing for large enterprises. It aims to advance existing business intelligence pricing models from policy driven to achieve deep pattern driven real-time pricing. The deep pattern mining addresses critical and under-developed knowledge discovery and data mining issues. Detailed research topics include a probabilistic data ....Deep Pattern Mining for Dynamic Real-time Enterprise Scale Pricing. This project aims to build a pricing framework, based on deep pattern mining, to enable dynamic real-time pricing for large enterprises. It aims to advance existing business intelligence pricing models from policy driven to achieve deep pattern driven real-time pricing. The deep pattern mining addresses critical and under-developed knowledge discovery and data mining issues. Detailed research topics include a probabilistic data model, an extracted deep feature representation, a deep pattern mining algorithm, and a prototype system for pricing determination. The project outcomes aim to empower enterprises with real-time dynamic pricing capability, as well as building theoretical foundations to strengthen world leadership by Australian businesses.Read moreRead less
Mining complex concurrency relationship patterns for dynamic customer/asset interaction modelling through novel industrial behaviour networks . This project will develop novel data mining algorithms to model the evolution of concurrency relationships between customers and assets. It will take into account multiple aspect factors for a business such as seasonality, government policy, and other external events, for making fast, accurate, and efficient business decisions.