Discovery Early Career Researcher Award - Grant ID: DE240100200
Funder
Australian Research Council
Funding Amount
$428,847.00
Summary
Cohesive Multipartite Subgraph Discovery in Large Heterogeneous Networks. This project aims to devise novel cohesive multipartite subgraph models and corresponding efficient search algorithms based on various applications. Significant advances in understanding big data will be enabled by the proposed novel theories and algorithms, which can leverage the value of heterogeneous network data and serve as the foundation of network analytics. Expected outcomes of this project include novel cohesive m ....Cohesive Multipartite Subgraph Discovery in Large Heterogeneous Networks. This project aims to devise novel cohesive multipartite subgraph models and corresponding efficient search algorithms based on various applications. Significant advances in understanding big data will be enabled by the proposed novel theories and algorithms, which can leverage the value of heterogeneous network data and serve as the foundation of network analytics. Expected outcomes of this project include novel cohesive multipartite subgraph models, efficient searching algorithms and platforms for heterogeneous networks. This should provide significant benefits for different organisations and a myriad of applications dealing with heterogeneous network data, including but not limited to e-commerce, cybersecurity, health and social networks.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100165
Funder
Australian Research Council
Funding Amount
$443,847.00
Summary
Evolving privacy and utility in data storage and publishing. This project aims to develop a distributed evolutionary computation-based framework to optimize data privacy and utility in distributed database systems. It intends to synchronously solve the conflicting challenges of privacy preservation and utility maintenance in multi-objective, dynamic, and multitasking scenarios. Expected outcomes include a new computation framework as a service and freely available distributed computation models, ....Evolving privacy and utility in data storage and publishing. This project aims to develop a distributed evolutionary computation-based framework to optimize data privacy and utility in distributed database systems. It intends to synchronously solve the conflicting challenges of privacy preservation and utility maintenance in multi-objective, dynamic, and multitasking scenarios. Expected outcomes include a new computation framework as a service and freely available distributed computation models, evolutionary algorithms, and knowledge-transfer strategies. Anticipated benefits include theoretical contributions to artificial intelligence, cyber security, distributed computation, and a service to eliminate data owners’ privacy concerns while guaranteeing the value of data in further utilization.Read moreRead less
Scaling Disk-Resident Learned Indexes For Database Systems. This project aims to investigate new disk-resident learned indexing algorithms to store and process data in database systems by advancing the state-of-the-art in memory-resident learned modeling. This project expects to generate new knowledge in the area of digital storage technologies utilising novel and efficient techniques in learned indexing for big data. This should provide significant benefits to enable modern database systems to ....Scaling Disk-Resident Learned Indexes For Database Systems. This project aims to investigate new disk-resident learned indexing algorithms to store and process data in database systems by advancing the state-of-the-art in memory-resident learned modeling. This project expects to generate new knowledge in the area of digital storage technologies utilising novel and efficient techniques in learned indexing for big data. This should provide significant benefits to enable modern database systems to scale with the massive growth of data, improve the efficiency of data processing, improve the effectiveness of projects that utilise big data, and dramatically reduce energy costs in Australian data centres when storing and retrieving data from databases and lower their carbon footprints.Read moreRead less
Empowering Next-Generation Spatial Digital Twins with Linked Spatial Data. This project aims to design novel algorithms for aligning and querying of spatial data from heterogeneous sources. Spatial data is being generated at an unprecedented rate due to the prevalence of mobile devices and ubiquitous connectivity, which enables a novel application, spatial digital twins. However, harnessing this data in spatial digital twins is hampered by the isolation of data from different sources. The projec ....Empowering Next-Generation Spatial Digital Twins with Linked Spatial Data. This project aims to design novel algorithms for aligning and querying of spatial data from heterogeneous sources. Spatial data is being generated at an unprecedented rate due to the prevalence of mobile devices and ubiquitous connectivity, which enables a novel application, spatial digital twins. However, harnessing this data in spatial digital twins is hampered by the isolation of data from different sources. The project will investigate algorithms to align and query spatial data from heterogeneous sources for high accessibility. It will enable novel applications with advanced spatial analytical querying needs, such as emergency planning, benefiting location-based service providers, urban planners, and emergency management agencies.Read moreRead less
Next Generation Spatial Data Management for Virtual Spatial Systems. This project aims to design novel spatial data retrieval methods for efficient and accurate querying of large datasets with location information. Spatial data is being generated at an unprecedented rate due to the prevalence of mobile devices and ubiquitous connectivity. However, harnessing this data is hampered by outdated and inefficient methods. The project will investigate data retrieval methods that self-optimise for high ....Next Generation Spatial Data Management for Virtual Spatial Systems. This project aims to design novel spatial data retrieval methods for efficient and accurate querying of large datasets with location information. Spatial data is being generated at an unprecedented rate due to the prevalence of mobile devices and ubiquitous connectivity. However, harnessing this data is hampered by outdated and inefficient methods. The project will investigate data retrieval methods that self-optimise for high query efficiency and accuracy, by utilising underlying real-world data patterns. It will enable novel applications for virtual spatial systems with large-scale querying needs, such as spatial digital twins and metaverses, benefiting location-based service providers, urban planners, and emergency management agencies.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100366
Funder
Australian Research Council
Funding Amount
$428,000.00
Summary
From data to fast insights: a database system for seamless data exploration. This project aims to develop a next-generation database platform for seamless data exploration, where users can interactively search for insights buried in the data, without a clear outcome in mind. Unlike today's database management systems, this platform does not require costly experts to tune the database for fast responses, and guides users towards finding insights. Using the latest advancements in machine learning ....From data to fast insights: a database system for seamless data exploration. This project aims to develop a next-generation database platform for seamless data exploration, where users can interactively search for insights buried in the data, without a clear outcome in mind. Unlike today's database management systems, this platform does not require costly experts to tune the database for fast responses, and guides users towards finding insights. Using the latest advancements in machine learning to facilitate data exploration and reduce the time and effort to discover insights, this open-source database platform should provide significant benefits to Australian businesses and boost scientific discovery, increasing Australia’s competitiveness in the global data-driven market. Read moreRead less
Situation-aware Multi-sided Personalised Analytics in Spatial Crowdsourcing. This project aims to create a next generation recommender system that enables enhanced task allocation and route recommendation on spatial crowdsourcing platforms. It expects to address key challenges in situation-aware reliable recommendation for big spatial crowdsourcing data, which is vital in improving users’ service experience and decision making. Expected outcomes of this project include advanced data models, effi ....Situation-aware Multi-sided Personalised Analytics in Spatial Crowdsourcing. This project aims to create a next generation recommender system that enables enhanced task allocation and route recommendation on spatial crowdsourcing platforms. It expects to address key challenges in situation-aware reliable recommendation for big spatial crowdsourcing data, which is vital in improving users’ service experience and decision making. Expected outcomes of this project include advanced data models, efficient algorithms and query techniques to create a Crowd-guided Advanced Spatial Crowdsourcing Analytics (CASCA) system that is effective, efficient, crowd-guided, and situation-aware. It will benefit crowdsourced media data analysis and big data fields, bringing economic and social benefits to Australian industries and users.Read moreRead less
Responsible modelling respecting privacy, data quality, and green computing. With the unprecedented growing impact of data on science, the economy and society, there comes the need for responsible data science practices which are accountable for the social good. This project aims to investigate the challenging problem of how to provide responsible data management, spanning across privacy-aware data exploration, resilient modelling to cope with imperfect data, and efficient model architectures fo ....Responsible modelling respecting privacy, data quality, and green computing. With the unprecedented growing impact of data on science, the economy and society, there comes the need for responsible data science practices which are accountable for the social good. This project aims to investigate the challenging problem of how to provide responsible data management, spanning across privacy-aware data exploration, resilient modelling to cope with imperfect data, and efficient model architectures for resource-constrained environments. This will be achieved by developing theories and techniques for complex real-world multi-modal data retrieval throughout the data life-cycle. The expected outcomes will significantly contribute to building capability in emerging technologies in the context of responsible data science. Read moreRead less
Towards knowledge discovery from imperfect and evolving data. Information extraction from data is critical, both to analyse and protect consumer data. However, many learning techniques are developed using perfect, static datasets, quite different to messy, ever-changing real-world data. This project aims to develop data analytics techniques that can extract accurate information in complex structures from imperfect/incomplete data that changes over time. Expected outcomes are a prototype tool, te ....Towards knowledge discovery from imperfect and evolving data. Information extraction from data is critical, both to analyse and protect consumer data. However, many learning techniques are developed using perfect, static datasets, quite different to messy, ever-changing real-world data. This project aims to develop data analytics techniques that can extract accurate information in complex structures from imperfect/incomplete data that changes over time. Expected outcomes are a prototype tool, tested on real datasets, that combines new techniques in data modelling, algorithm development, and system design. Likely benefits are enhanced Australia's competence in data science through student training and new, robust data tools relevant to critical sectors such as cybersecurity, healthcare, and defence.Read moreRead less
Short Sequence Representation Learning with Limited Supervision . Predicting events based on short text and video data is widely found in real-world applications such as online crime detection, cyber-attack identification, and public security protection. However, to develop such an effective prediction model is very difficult due to the problems such as limited supervision, heterogeneous multiple sources, and missing and low-quality data. This project is to tackle these challenges. Expected outc ....Short Sequence Representation Learning with Limited Supervision . Predicting events based on short text and video data is widely found in real-world applications such as online crime detection, cyber-attack identification, and public security protection. However, to develop such an effective prediction model is very difficult due to the problems such as limited supervision, heterogeneous multiple sources, and missing and low-quality data. This project is to tackle these challenges. Expected outcome of this project will lay a theoretical foundation for effective short sequence representation learning and build next-generation intelligent systems. This should benefit our society and economy through the applications of multimodality-integrated video technologies for cybersecurity and public safety. Read moreRead less