Data sharing with strong privacy against inference attacks. This project aims to develop theories and techniques for strong protection of personal information in sharing large datasets such as national health data or census records. It intends to achieve this through developing new information theoretic methods for synthesising datasets with proven high fidelity and protection against re-identification and inference attacks, where attackers try to learn probability of sensitive data. The expecte ....Data sharing with strong privacy against inference attacks. This project aims to develop theories and techniques for strong protection of personal information in sharing large datasets such as national health data or census records. It intends to achieve this through developing new information theoretic methods for synthesising datasets with proven high fidelity and protection against re-identification and inference attacks, where attackers try to learn probability of sensitive data. The expected outcomes are algorithms for public and private sector data curators to dial up or down their data access arrangements based on privacy risks and fidelity demands linked with different data types and uses. This project intends to enable Australians to securely benefit from valuable data in decision making.Read moreRead less
Parameter estimation for genetic time-series data: Theory and methods. This project aims to develop a novel computational framework for solving parameter estimation problems in evolutionary modelling by leveraging genetic time-series data measured by Next-Generation Sequencing technologies. It will foster international collaboration, cutting across disciplines. By introducing new techniques from signal processing and tools from random matrix theory commonly employed for mobile wireless communica ....Parameter estimation for genetic time-series data: Theory and methods. This project aims to develop a novel computational framework for solving parameter estimation problems in evolutionary modelling by leveraging genetic time-series data measured by Next-Generation Sequencing technologies. It will foster international collaboration, cutting across disciplines. By introducing new techniques from signal processing and tools from random matrix theory commonly employed for mobile wireless communications, it seeks to design scalable inference methods for resolving mutational fitness effects from genetic time-series measurements of complex evolving populations. This would enable new understanding of complex adaptive systems, such as pathogen evolution, host-immune dynamics, and acquisition of drug resistance. Read moreRead less
Explicit methods in number theory: Computation, theory and application. This project aims to use explicit estimates to unify three problems in number theory: primitive roots, Diophantine quintuples, and linear independence of zeroes of the Riemann zeta-function. It will use computational and analytic number theory to reduce the quintuples problem to a soluble level. Pursuing relations between the zeta zeroes will overhaul many current results. This project will apply its findings about primitive ....Explicit methods in number theory: Computation, theory and application. This project aims to use explicit estimates to unify three problems in number theory: primitive roots, Diophantine quintuples, and linear independence of zeroes of the Riemann zeta-function. It will use computational and analytic number theory to reduce the quintuples problem to a soluble level. Pursuing relations between the zeta zeroes will overhaul many current results. This project will apply its findings about primitive roots to signal processing, cryptography and cybersecurity.Read moreRead less
Deep Interaction Learning in Unlabelled Big Data and Complex Systems. This project aims to effectively model intricate interactions deeply embedded in unlabelled big data and complex systems, which are often hierarchical, heterogeneous, contextual, dynamic or even contrastive. Learning such interactions is the keystone of robust data science and for realizing the value of big data but it poses significant challenges and knowledge gaps to existing data analytics and learning systems. The expected ....Deep Interaction Learning in Unlabelled Big Data and Complex Systems. This project aims to effectively model intricate interactions deeply embedded in unlabelled big data and complex systems, which are often hierarchical, heterogeneous, contextual, dynamic or even contrastive. Learning such interactions is the keystone of robust data science and for realizing the value of big data but it poses significant challenges and knowledge gaps to existing data analytics and learning systems. The expected outcomes include new-generation theories and methods for the unsupervised learning of complex interactions in real-life big data, which are anticipated to enable the intrinsic processing of big data complexities and substantially enhance Australia’s leadership in frontier data science research and applications. Read moreRead less
Sensing biomechanical forces in the heart. Mechanosensitive ion channels are key molecules that define how each heart cell interacts with their physical environment. Yet how they enable cells to decode biomechanical cues remains poorly understood. At the heart of this problem is a lack of tools to quantify the force required for activation. This project aims to develop novel technologies to record the activity of these essential channels in a critical cell type within the heart, and use this inf ....Sensing biomechanical forces in the heart. Mechanosensitive ion channels are key molecules that define how each heart cell interacts with their physical environment. Yet how they enable cells to decode biomechanical cues remains poorly understood. At the heart of this problem is a lack of tools to quantify the force required for activation. This project aims to develop novel technologies to record the activity of these essential channels in a critical cell type within the heart, and use this information in addition to micro-engineering approaches to fully understand the role of these channels in force sensing and generation, at both the single cell and micro-tissue levels. This knowledge and technology has broad utility that extends far beyond cardiac biology into multiple fields.Read moreRead less
Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to vi ....Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to video surveillance applications, which can enhance Australia’s homeland security.Read moreRead less
Investigation of the mechanisms underlying successful placentation. The overall aim of this project is to provide novel insights into the basic cellular processes that underpin placental development and to improve our ability to manipulate mammalian reproduction, both human and animal. The placenta is critical for intrauterine development because it determines the level of nutrition, oxygenation and maternal tolerance to the developing foetus. The project intends to explore the role of prorenin ....Investigation of the mechanisms underlying successful placentation. The overall aim of this project is to provide novel insights into the basic cellular processes that underpin placental development and to improve our ability to manipulate mammalian reproduction, both human and animal. The placenta is critical for intrauterine development because it determines the level of nutrition, oxygenation and maternal tolerance to the developing foetus. The project intends to explore the role of prorenin and its receptor as a novel mechanism driving placentation. Applications for expected project outcomes may include improved breeding of threatened animal species and economically valuable domestic animals as well as improved health care and fertility control for domesticated pets and feral animals. Read moreRead less
Big Data Machines: Internet-Scale Machine Learning Techniques to Combat the Curse of Big Data. The advent of “big data” in business, government, science, social networks, the internet, etc. creates opportunity in business and commercial domains. Big data also raises issues of increasing volume, variety, dimensionality and categories in open domain big data applications, which this project will solve by developing novel machine learning techniques, including theoretical foundations, a big data ma ....Big Data Machines: Internet-Scale Machine Learning Techniques to Combat the Curse of Big Data. The advent of “big data” in business, government, science, social networks, the internet, etc. creates opportunity in business and commercial domains. Big data also raises issues of increasing volume, variety, dimensionality and categories in open domain big data applications, which this project will solve by developing novel machine learning techniques, including theoretical foundations, a big data machine learning framework and open source website. The outcomes of this project will provide frontier technologies for big data analysis that will have social and economic impact in such areas as social media computing, bioinformatics and business intelligence, and enhance Australia’s global position in the pattern recognition and data mining communities.Read moreRead less
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
Novel models to advance our understanding of mammalian development. This project aims to add to the understanding of cellular processes underpinning mammalian development. Protein phosphorylation is a dynamic process regulated by both protein kinases and protein phosphatases. While the role of kinases in cellular functions are well defined, the roles of protein phosphatases are not well understood. Using a range of laboratory models this project aims to discover the function of the phosphatase P ....Novel models to advance our understanding of mammalian development. This project aims to add to the understanding of cellular processes underpinning mammalian development. Protein phosphorylation is a dynamic process regulated by both protein kinases and protein phosphatases. While the role of kinases in cellular functions are well defined, the roles of protein phosphatases are not well understood. Using a range of laboratory models this project aims to discover the function of the phosphatase PP2A, in cell proliferation, survival, differentiation and DNA damage repair. The anticipated outcome is an improved understanding of all stages of mammalian development. This will provide significant benefits in the biotechnology, chemical and pharmaceutical industries.Read moreRead less