Learning the Focus of Attention to Detect Distributed Coordinated Attacks. Cyber security analysts need to detect and respond to attacks as soon as possible, to minimise the damage attackers can inflict. However, the growth in highly distributed attacks that span multiple networks has meant that massive volumes of data need to be analysed. While machine learning techniques can help filter the data, we need techniques that can automatically provide a focus of attention for analysts on the most re ....Learning the Focus of Attention to Detect Distributed Coordinated Attacks. Cyber security analysts need to detect and respond to attacks as soon as possible, to minimise the damage attackers can inflict. However, the growth in highly distributed attacks that span multiple networks has meant that massive volumes of data need to be analysed. While machine learning techniques can help filter the data, we need techniques that can automatically provide a focus of attention for analysts on the most relevant observations. Our aim is to devise a novel suite of attention mechanisms that can focus the search of machine learning techniques for cyber security. The results of this project will improve the accuracy and efficiency of detecting distributed attacks across multiple networks.Read moreRead less
Low-cost Sensing Methods and Hybrid Learning Models. This project aims to revolutionise the theory and practice of sensing and monitoring by developing novel Artificial Intelligence and Internet of Things technologies. This project expects to generate new knowledge in the area of Artificial Intelligence of Things by combining sensing, machine learning, and big data analytics. Expected outcomes of this project include novel low-cost sensing methods and new hybrid machine learning models for predi ....Low-cost Sensing Methods and Hybrid Learning Models. This project aims to revolutionise the theory and practice of sensing and monitoring by developing novel Artificial Intelligence and Internet of Things technologies. This project expects to generate new knowledge in the area of Artificial Intelligence of Things by combining sensing, machine learning, and big data analytics. Expected outcomes of this project include novel low-cost sensing methods and new hybrid machine learning models for predictive sensory data analytics. This should provide significant benefits, such as substantially reduced operating and service costs and improved accuracy for real-time monitoring in the fields where cheap-to-implement and easy-to-service monitoring systems over large geographical areas are imperative.Read moreRead less
Using data mining methods to remove uncertainties in sensor data streams. This project will develop key techniques for removing uncertainties in sensor data streams and thus improve the monitoring quality of sensor networks. The expected outcomes will benefit Australia by enabling improved, lower-cost monitoring of natural resources and management of stock raising.
Deep Data Mining for Anomaly Prediction from Sensor Data Streams. Sensor data streams are crucial for anomaly predictions in real-life monitoring. However, balancing efficiency and accuracy in predicting anomalies with sensor streams is a great challenge; it requires new techniques that go beyond detecting anomalies and predicting trends. This project will develop a deep mining method for anomaly prediction from sensor streams; it will comprise mining algorithms at various levels - from compress ....Deep Data Mining for Anomaly Prediction from Sensor Data Streams. Sensor data streams are crucial for anomaly predictions in real-life monitoring. However, balancing efficiency and accuracy in predicting anomalies with sensor streams is a great challenge; it requires new techniques that go beyond detecting anomalies and predicting trends. This project will develop a deep mining method for anomaly prediction from sensor streams; it will comprise mining algorithms at various levels - from compressing massive raw data, to recognition of abnormal waveforms preceding anomalies, and to retrieving and summarising similar past anomalies for creating descriptions of future anomalies. The project will demonstrate our method in health/environment monitoring applications, and its adoption will save resources, money and lives.Read moreRead less
Deep analytics of non-occurring but important behaviours. This project aims to build a systematic theory for the deep analytics of complex and important occurring and non-occurring behaviours. Behaviours that should occur but do not take place, called non-occurring behaviours (NOB), are widely evident but easily overlooked, such as missed important medical treatments. While often occurring behaviours are focused, such NOB may be associated with significant effects such as a threat to health. Thi ....Deep analytics of non-occurring but important behaviours. This project aims to build a systematic theory for the deep analytics of complex and important occurring and non-occurring behaviours. Behaviours that should occur but do not take place, called non-occurring behaviours (NOB), are widely evident but easily overlooked, such as missed important medical treatments. While often occurring behaviours are focused, such NOB may be associated with significant effects such as a threat to health. This project expects to fill the knowledge gaps in representing, analysing and evaluating NOB complexities and impact, with significant benefits for the evidence-based detection, prediction and risk management of covert NOB applications and their important effects.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
Knowledge discovery from data in the context of prior beliefs. This project will invent user-centric technologies for discovering knowledge from data that are distinguished by taking account of the user's beliefs, enabling more useful discoveries to be made. This project will also invent methods that identify the relative potential value of those discoveries, helping the user derive greater value from their data assets.
Time Series Classification for Complex Dynamic Global Problems. This project aims to increase understanding of complex dynamic processes by creating new ways of analysing large quantities of data collected over time. These new approaches will be specifically designed to greatly improve the understanding obtained from time varying data for trillions of global earth observation data points in an application-agnostic way that is applicable to many tasks. The outcomes are expected to advance the the ....Time Series Classification for Complex Dynamic Global Problems. This project aims to increase understanding of complex dynamic processes by creating new ways of analysing large quantities of data collected over time. These new approaches will be specifically designed to greatly improve the understanding obtained from time varying data for trillions of global earth observation data points in an application-agnostic way that is applicable to many tasks. The outcomes are expected to advance the theory and practice of time-series data analysis and transform the analysis of complex dynamics. This should support innovation in industry, commerce, government and research and magnify benefit from many data investments including the $1 billion Australian governments invest annually in satellite imaging.Read moreRead less
Combining generative and discriminative strategies to facilitate efficient and effective learning from big data. Effective extraction of information from massive data stores is increasingly problematic as data quantities continue to grow rapidly. Quite simply, effective techniques for learning from small data do not scale. However, the problem is even worse than this. Big data contain more information than the small data in which context most state-of-the-art learning algorithms have been develo ....Combining generative and discriminative strategies to facilitate efficient and effective learning from big data. Effective extraction of information from massive data stores is increasingly problematic as data quantities continue to grow rapidly. Quite simply, effective techniques for learning from small data do not scale. However, the problem is even worse than this. Big data contain more information than the small data in which context most state-of-the-art learning algorithms have been developed. For small data overly detailed classifiers will overfit the data and so should be avoided. In contrast, big data provide fine detail and hence will benefit new types of learner that can capture it. This project will deliver learners that are not only capable of capturing this detail, but do so with the efficiency required to process terabytes of data.Read moreRead less
Privacy-preserving record linkage on multiple large databases. Record linkage has been recognised as a crucial infrastructure component in many information systems, however privacy concerns commonly prevent the linking of databases that contain personal information. This project will develop techniques that will enable the linking of multiple large databases without revealing any private information.