Mining multi-typed and dynamic graphs. Large volumes of data collected nowadays from real-world applications are often represented as graphs. The nodes and the edges of such graphs represent different types of entities and interactions, and they have time information. This project will develop algorithms that mine efficiently such multi-typed and dynamic graphs.
Next generation real-time trajectory mining for travel and transportation decision support. Mining human and vehicle trajectories in real time will enable a suite of next-generation applications such as traffic overload prediction, real-time event detection and route recommendation. This project will develop novel techniques for immediate mining of massive volumes of trajectory data as it is being continuously generated.
Comparative Biogeography of Australasian biota. Establishing an internationally recognised biogeographical research program will help scientists, policy makers and the public understand the past and future distribution patterns of the plants and animals of Australia. Discovering these patterns will help conservation biologists and government implement the right policies and practices to deal with biodiversity loss and climate change.
Deep Weak Learning for Morphology Analysis of Micro and Nanoscale Images. This project will develop novel methods for automated discovery and quantification of image phenotypes from micro and nanoscale images. The outcome will be an advance of the state of the art in biomedical image analysis with a particular focus on generalized weakly-supervised deep learning models for morphological feature representation. The methodologies will transform the deep learning pipeline for real biomedical imagin ....Deep Weak Learning for Morphology Analysis of Micro and Nanoscale Images. This project will develop novel methods for automated discovery and quantification of image phenotypes from micro and nanoscale images. The outcome will be an advance of the state of the art in biomedical image analysis with a particular focus on generalized weakly-supervised deep learning models for morphological feature representation. The methodologies will transform the deep learning pipeline for real biomedical imaging scenarios with high heterogeneity and limited training data. The frameworks will facilitate high-throughput processing for a wide range of microscopy image modalities and biological applications, and potentially become the next generation computational platform to support fundamental research in human biology.Read moreRead less
Taming Large-Volume Dynamic Graphs in the Cloud. This project aims to develop efficient and scalable algorithms to process large-volume dynamic graphs in the cloud. The project expects to address key challenges and lay theoretical foundations in large-volume dynamic graph processing, which plays an important role in developing general-purpose, real-time structural search engines. Expected outcomes of this project include theoretical foundations and scalable algorithms to process big graphs that ....Taming Large-Volume Dynamic Graphs in the Cloud. This project aims to develop efficient and scalable algorithms to process large-volume dynamic graphs in the cloud. The project expects to address key challenges and lay theoretical foundations in large-volume dynamic graph processing, which plays an important role in developing general-purpose, real-time structural search engines. Expected outcomes of this project include theoretical foundations and scalable algorithms to process big graphs that evolve rapidly over time. These enable users to monitor and analyse structural information in large dynamic networks in real time. The project expects to open up a new research direction for graph processing to enrich frontier technologies and benefit many key applications in Australia.Read moreRead less
Efficient and Scalable Processing of Dynamic Heterogeneous Graphs . This project aims to develop efficient and scalable algorithms to process large-scale dynamic heterogeneous graphs where graph nodes and edges are of multiple types and the graph structure updates dynamically. Key challenges are expected to be addressed including complex structure, high speed, and large volume of dynamic heterogeneous graphs. The anticipated outcomes include novel computing paradigms, algorithms, indexing, incre ....Efficient and Scalable Processing of Dynamic Heterogeneous Graphs . This project aims to develop efficient and scalable algorithms to process large-scale dynamic heterogeneous graphs where graph nodes and edges are of multiple types and the graph structure updates dynamically. Key challenges are expected to be addressed including complex structure, high speed, and large volume of dynamic heterogeneous graphs. The anticipated outcomes include novel computing paradigms, algorithms, indexing, incremental computation, distributed algorithms as well as a system prototype to demonstrate the practical value. Success of this project will open up a new research direction to enrich frontier technologies and benefit many key applications in Australia including cybersecurity, e-commerce, health and social networks.Read moreRead less
Efficient Management of Things for the Future World Wide Web. The future World Wide Web will connect billions of physical objects, which will offer exciting capabilities to change the world and improve the quality of human lives, just as what the Web has done in the past 20 years. Effectively and efficiently managing things is one inevitable challenge in this new era and is much more complicated than managing traditional Web documents. This project aims to focus on this key problem and develop n ....Efficient Management of Things for the Future World Wide Web. The future World Wide Web will connect billions of physical objects, which will offer exciting capabilities to change the world and improve the quality of human lives, just as what the Web has done in the past 20 years. Effectively and efficiently managing things is one inevitable challenge in this new era and is much more complicated than managing traditional Web documents. This project aims to focus on this key problem and develop novel techniques for linking resource-constrained things to the Web, searching them using a new search engine, as well as discovering latent relationships among things for advanced management tasks such as things recommendation and composition.Read moreRead less
Effective, efficient and scalable processing of big geo-textual streams. This project aims to develop novel approaches to realise the value of geo-textual data, which carries both location and textual information. The project expects to address three key challenges brought by massive volumes and high speeds of big geo-textual streams: better user experiences; increased efficiency; and greater scalability in query processing. The project should provide individuals, business and government agencie ....Effective, efficient and scalable processing of big geo-textual streams. This project aims to develop novel approaches to realise the value of geo-textual data, which carries both location and textual information. The project expects to address three key challenges brought by massive volumes and high speeds of big geo-textual streams: better user experiences; increased efficiency; and greater scalability in query processing. The project should provide individuals, business and government agencies with the ability to unlock key values in the overwhelming volume of high-speed, big geo-textual streams for important usage in many emerging key applications, such as social media analytics, location-based services, social networks, e-marketing and cybersecurity.Read moreRead less
Advanced search of cohesive subgraphs in big graphs. This project aims to study advanced cohesive subgraph searches, as well as design efficient and scalable techniques to conduct such searches. Cohesive subgraph search over big graphs is demanded by many applications, such as risk management, analysis of users’ behaviours, cybersecurity, crime detection, social marketing and community search. This project will develop, analyse, implement, and evaluate novel indexing and data processing techniqu ....Advanced search of cohesive subgraphs in big graphs. This project aims to study advanced cohesive subgraph searches, as well as design efficient and scalable techniques to conduct such searches. Cohesive subgraph search over big graphs is demanded by many applications, such as risk management, analysis of users’ behaviours, cybersecurity, crime detection, social marketing and community search. This project will develop, analyse, implement, and evaluate novel indexing and data processing techniques to support a set of advanced cohesive subgraph searches. This will provide significant benefits to many applications such as the next generation of fintech, cybersecurity, e-commerce, crime detection and social network analysis.Read moreRead less
AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing n ....AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing novel deep learning algorithms. The new algorithms will benefit a wide range of applications, e.g. to effectively use car crash training samples for accurately identifying potential road crashes in transport and to effectively use rare medical imaging training data for robustly diagnosing diseases in health.Read moreRead less