Privacy-preserving cloud data mining-as-a-service. This project aims to explore practical privacy-preserving solutions for cloud data mining-as-a-service based on the Intel Software Guard Extensions (SGX) technology. The research addresses privacy concerns of users when outsourcing data mining needs to the cloud. These concerns have increased as more businesses evaluate data mining-as-an outsourced service due to lack of expertise or computation resources. The expected outcomes from the research ....Privacy-preserving cloud data mining-as-a-service. This project aims to explore practical privacy-preserving solutions for cloud data mining-as-a-service based on the Intel Software Guard Extensions (SGX) technology. The research addresses privacy concerns of users when outsourcing data mining needs to the cloud. These concerns have increased as more businesses evaluate data mining-as-an outsourced service due to lack of expertise or computation resources. The expected outcomes from the research will include new data privacy models, new privacy-preserving data mining algorithms, and a prototype of cloud data mining software. These will help businesses cut costs for data mining and privacy protection, and provide significant benefits toward helping Australia achieve its national cyber security strategy and potentially provide economic impact from commercialisation of new software technology for the industry partner.Read moreRead less
A data science framework for modelling disease patterns from medical images. A data science framework for modelling disease patterns from medical images. This project aims to extract models of disease patterns from medical imaging data, using deep learning, smart image processing, machine learning, and statistical modelling to quantify and model patterns conventional methods cannot detect. These disease models are expected to improve understanding of particular diseases and enable precision medi ....A data science framework for modelling disease patterns from medical images. A data science framework for modelling disease patterns from medical images. This project aims to extract models of disease patterns from medical imaging data, using deep learning, smart image processing, machine learning, and statistical modelling to quantify and model patterns conventional methods cannot detect. These disease models are expected to improve understanding of particular diseases and enable precision medicine, which recognises that there are important differences between individuals with a particular disease, and that when patients are separated into sub-populations with similar disease patterns, treatment can be tailored to these sub-populations.Read moreRead less
Machine Learning for Fracture Risk Assessment from Simple Radiography. This project aims to develop a novel, reliable, low-cost system to detect poor bone health and assess fracture risk to help to prevent and manage osteoporosis-related fractures. Currently, osteoporosis-related fractures cost our health system millions of dollars annually and costs are increasing with our ageing population. Early detection of poor bone health will improve the effectiveness of preventive measures and ease this ....Machine Learning for Fracture Risk Assessment from Simple Radiography. This project aims to develop a novel, reliable, low-cost system to detect poor bone health and assess fracture risk to help to prevent and manage osteoporosis-related fractures. Currently, osteoporosis-related fractures cost our health system millions of dollars annually and costs are increasing with our ageing population. Early detection of poor bone health will improve the effectiveness of preventive measures and ease this burden. Current methods include unreliable, crude clinical and visual guides that suggest osteoporosis screening. The project plans to develop a novel system by applying machine learning algorithms to radiology data which is commonly captured for diagnosing other conditions.Read moreRead less
Biomedical Visual Image Analytics for Multi-disciplinary Retrieval. The project aims to develop a framework to provide users with the interactive access to information that is necessary for the best collaborative decision-making. Visual analytics theory is becoming increasing valuable for managing ‘big data’ because it can provide interactive and intuitive understanding of the rich information embedded within complex data and decision support systems. There are, however, fundamental challenges t ....Biomedical Visual Image Analytics for Multi-disciplinary Retrieval. The project aims to develop a framework to provide users with the interactive access to information that is necessary for the best collaborative decision-making. Visual analytics theory is becoming increasing valuable for managing ‘big data’ because it can provide interactive and intuitive understanding of the rich information embedded within complex data and decision support systems. There are, however, fundamental challenges that currently prevent visual analytics from being routinely applied to multi-disciplinary collaboration, which is now ‘the norm’ to solve large complicated problems where there is significant social impact. This project aims to address these challenges and improve visual analytics theory by developing a biomedical visual image analytics framework that enables interactive information retrieval of multidisciplinary databases.Read moreRead less
Probabilistic search over large-scale uncertain graphs. Efficiently conducting structure-based search is fundamental in many real applications. The project aims to develop effective searching techniques for large-scale imprecise and/or uncertain graphs. This project will develop, analyse, implement, and evaluate novel indexing and query processing techniques to efficiently conduct structure-based probabilistic queries over large uncertain graphs, including structure search, structure similarity ....Probabilistic search over large-scale uncertain graphs. Efficiently conducting structure-based search is fundamental in many real applications. The project aims to develop effective searching techniques for large-scale imprecise and/or uncertain graphs. This project will develop, analyse, implement, and evaluate novel indexing and query processing techniques to efficiently conduct structure-based probabilistic queries over large uncertain graphs, including structure search, structure similarity search, all-matches, vertex-pair similarity search and top-k search. The success of this project will be an important complement to the current development of graph database management technology and will bring considerable social, economic and technological benefits to Australia.Read moreRead less
Hardware-based accelerators for real-time machine learning. This project will tackle the challenge of applying real-time machine learning to massive high-frequency data. This project will leverage advancements in machine learning and hardware synthesis to implement computationally complex machine-learning algorithms on hardware-accelerated platforms, avoiding overhead delays incurred by software running on a processor.
Ranking complex objects in a multi-dimensional space. The project aims to develop novel, advanced techniques to rank complex objects in a multi-dimensional space. The success of the project not only brings a breakthrough in technology development but also provides training for high quality personnel in this important and growing area, and brings considerable economic and social benefits to Australia.
Multiview Complete Space Learning for Sparse Camera Network Research. Data analytics in video surveillance and social computing is a problem because data are represented by multiple heterogeneous features. This project will develop a multiview complete space learning framework to exploit heterogeneous properties to represent images obtained from sparse camera networks. It will integrate multiple features to identify people and understand behaviour, to build a database of activities occurring in ....Multiview Complete Space Learning for Sparse Camera Network Research. Data analytics in video surveillance and social computing is a problem because data are represented by multiple heterogeneous features. This project will develop a multiview complete space learning framework to exploit heterogeneous properties to represent images obtained from sparse camera networks. It will integrate multiple features to identify people and understand behaviour, to build a database of activities occurring in a wide area of surveillance. It will expand frontier technologies and safeguard Australia by providing warnings for hazardous (for example, overcrowding, trespassing), criminal, and terrorist situations. Results will be applicable internationally and enhance Australia’s role in machine learning and computer vision communities.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE120102144
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
Continuously monitoring uncertain objects in a multi-dimensional space. The project aims to develop novel, advanced techniques to continuously monitor uncertain objects. The success of the project not only brings breakthroughs in technology development but also provides training for high quality personnel in this important and growing area, and brings considerable economic and social benefits to Australia.
Cross-domain knowledge transfer for data-driven decision making. This project aims to develop a set of cross-domain knowledge transfer methodologies to support Data-Driven Decision-Making (D3M) systems. D3M is essential in business, particularly for ever-changing environments in today’s big data era, but D3Ms for solving new problems may face in-domain data insufficiency. The challenge is to effectively transfer knowledge from multiple heterogeneous source domains. The outcomes are expected to t ....Cross-domain knowledge transfer for data-driven decision making. This project aims to develop a set of cross-domain knowledge transfer methodologies to support Data-Driven Decision-Making (D3M) systems. D3M is essential in business, particularly for ever-changing environments in today’s big data era, but D3Ms for solving new problems may face in-domain data insufficiency. The challenge is to effectively transfer knowledge from multiple heterogeneous source domains. The outcomes are expected to transfer implicit and explicit knowledge, handle discrete and continuous outputs, and support business decision-making, which should advance the discipline of transfer learning and data-driven DSS in dynamically changing environments.Read moreRead less