On effectively modelling and efficiently discovering communities from large networks. Finding and maintaining close communities from very large scale, dynamically changing networks is interesting and challenging. This project aims to develop new techniques to identify such communities as fast as possible through exploiting the rich semantics and individual relationships within the communities.
Making sense of trajectory data: a database approach. This project investigates new challenges related to providing functionality, flexibility and efficiency for large scale trajectory data management and processing. The expected outcome includes significant technical contributions in novel indexing structures and advanced query processing methods for making better use of rich trajectory data.
Discovery Early Career Researcher Award - Grant ID: DE140100679
Funder
Australian Research Council
Funding Amount
$395,220.00
Summary
Real-time query processing over multi-dimensional uncertain data streams. Real-time query processing of multi-dimensional uncertain data streams is fundamental in many applications such as environmental monitoring and location based services. This project aims to develop effective techniques to explore the massive multi-dimensional uncertain data streams in real time. The project will develop, analyse, implement and evaluate novel indexing and query processing techniques to effectively and effic ....Real-time query processing over multi-dimensional uncertain data streams. Real-time query processing of multi-dimensional uncertain data streams is fundamental in many applications such as environmental monitoring and location based services. This project aims to develop effective techniques to explore the massive multi-dimensional uncertain data streams in real time. The project will develop, analyse, implement and evaluate novel indexing and query processing techniques to effectively and efficiently support a set of primitive queries including rank-based queries, dominance-based queries and proximity-based queries. The results of this project will be an important complement to the development of data stream systems and will bring considerable social, economic and technological benefits to Australia.Read moreRead less
Monitoring social events for user online behaviour analytics. This project aims to investigate the influence of public attention on steering user online behaviour. The exponential growth of online behaviour data makes online behaviour analytics increasingly important in social, commercial and political environments, but existing methods rely on user profiles only. The project will unify external social events with user profiles for behaviour analytics, and develop approaches for event database i ....Monitoring social events for user online behaviour analytics. This project aims to investigate the influence of public attention on steering user online behaviour. The exponential growth of online behaviour data makes online behaviour analytics increasingly important in social, commercial and political environments, but existing methods rely on user profiles only. The project will unify external social events with user profiles for behaviour analytics, and develop approaches for event database indexing, event-influenced behaviour modelling and prediction. The success of this project is expected to enhance users’ online experience and improve e-commerce’s market value.Read moreRead less
Taming the uncertainty in trajectory data. This project aims to develop effective and efficient methods to manage large scale uncertain trajectory data. It provides individuals, business, government and social groups the ability to explore significant uncertain trajectories and their patterns, for important usages in location based services, logistic, transportation and tourism.
Deep attribute-aware hashing for cross retrieval. This project aims to enable individuals, industries and governments, to freely access vital and linked information carried in different media types from different sources by developing a deep attribute-aware framework that embeds heterogeneous features into a shared data space to achieve effective and efficient cross system information retrieval. With the proliferation of heterogeneous data sources, there is an urgent need to enable search and re ....Deep attribute-aware hashing for cross retrieval. This project aims to enable individuals, industries and governments, to freely access vital and linked information carried in different media types from different sources by developing a deep attribute-aware framework that embeds heterogeneous features into a shared data space to achieve effective and efficient cross system information retrieval. With the proliferation of heterogeneous data sources, there is an urgent need to enable search and retrieval across different media types and domains. The framework developed by the project uses deep learning methods to develop meaningful image attributes to positively bridge the modality gap and the domain gap when hash functions are affixed to data. This project will significantly advance the research of multimedia retrieval, and benefit a series of related research problems whenever heterogeneous multimedia data are involved in their applications.Read moreRead less
Synergising multimedia content understanding with social data analysis. This project aims to develop novel approaches to explore synergies within big social multimedia data from both social and multimedia perspective. It provides individuals, groups, and businesses the ability to tap into the wisdom of crowds to enlarge knowledge base, enhance user experience, understand the pulse of crowds and make informed decision.
Techniques for active conceptual modelling and guided data mining for rapid knowledge discovery. Quick, accurate responses to rapidly evolving phenomena are essential. This project will develop a platform able to accept data from a variety of sources in advance of the full definition of the associated conceptual model. The project will facilitate rapid querying and direct manipulation of the mining process allowing fast, user-oriented results.
Continuous intent tracking for virtual assistance using big contextual data. Recently launched Virtual Assistant products such as Amazon Echo and Google Home are commanded by voice and can call apps to do simple tasks like setting timers and playing music. The next-generation virtual assistants will recommend things to be done proactively rather than waiting for commands passively. This project aims to develop algorithms that can predict what a user intends to do and therefore help virtual assis ....Continuous intent tracking for virtual assistance using big contextual data. Recently launched Virtual Assistant products such as Amazon Echo and Google Home are commanded by voice and can call apps to do simple tasks like setting timers and playing music. The next-generation virtual assistants will recommend things to be done proactively rather than waiting for commands passively. This project aims to develop algorithms that can predict what a user intends to do and therefore help virtual assistants make recommendations that suit users’ needs accurately. It will benefit many service industry sectors of Australia by enabling virtual assistants to provide services proactively.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE130101061
Funder
Australian Research Council
Funding Amount
$373,697.00
Summary
Personal safety in the city: design solutions for after dark. The research will provide insights into the potential for mobile technology to be designed to enhance personal safety in urban environments at night. It will do so by identifying individual personal harm reduction and safety strategies, and examining the opportunities to use technology to amplify these strategies.