Intelligent techniques to exploit the dynamic temporal structure in detection of attacks in credit application fraud. Obtaining credit using fraudulent information costs financial institutions billions of dollars. This project develops fraud detection methods in credit applications, working with credit bureau data. Existing fraud detection models are mostly applicable to transaction fraud, rather than application fraud, and are static. Fraudsters however constantly change their method of attack. ....Intelligent techniques to exploit the dynamic temporal structure in detection of attacks in credit application fraud. Obtaining credit using fraudulent information costs financial institutions billions of dollars. This project develops fraud detection methods in credit applications, working with credit bureau data. Existing fraud detection models are mostly applicable to transaction fraud, rather than application fraud, and are static. Fraudsters however constantly change their method of attack. The temporal characteristics of fraud attacks provide an additional source of information that can be exploited to gain increased predictive power. We propose a hybrid intelligent approach to construct models that are sensitive to the temporal dynamics of fraud attacks, and evolve to acknowledge the changing behaviour of fraudsters.Read moreRead less
Improving the modelling of insolvency risk and financial health assessment of global companies using hybrid intelligent techniques. The social and economic impacts of corporate collapses are severe, and much research has modelled financial health and insolvency risk of companies. Most research, however, uses simple and out-dated financial ratios used by Altman (1968), and attempts to develop a universal model valid for specific (non-global) markets. Our approach is to improve the relevance of th ....Improving the modelling of insolvency risk and financial health assessment of global companies using hybrid intelligent techniques. The social and economic impacts of corporate collapses are severe, and much research has modelled financial health and insolvency risk of companies. Most research, however, uses simple and out-dated financial ratios used by Altman (1968), and attempts to develop a universal model valid for specific (non-global) markets. Our approach is to improve the relevance of the information provided to the models (including measures of strategy, recent accounting metrics, global context). We also challenge the merits of a universal model by developing and testing a novel hybrid intelligent approach combining neural networks, genetic algorithms and self-organising maps, applicable to global markets.Read moreRead less
Exposing the anonymous attacker: detecting identity crimes using real-time entity resolution on large dynamic databases. Given the increasingly large costs of identity crimes in Australia, developing improved electronic identity verification techniques is highly significant in reducing losses from such crimes, making the Australian economy more competitive, and increasing consumer confidence in Australian financial institutions. Veda Advantage is widely used for identity verification by Australi ....Exposing the anonymous attacker: detecting identity crimes using real-time entity resolution on large dynamic databases. Given the increasingly large costs of identity crimes in Australia, developing improved electronic identity verification techniques is highly significant in reducing losses from such crimes, making the Australian economy more competitive, and increasing consumer confidence in Australian financial institutions. Veda Advantage is widely used for identity verification by Australian financial service providers, so the benefits of the techniques developed in this project will automatically flow through to the Australian community. These techniques will be sufficiently generic to be of use for real-time identity verification in a broad range of applications, including e-Government portals, electronic banking, online stores, or national security systems.Read moreRead less
Automatic real-time detection of infiltrated objects for security of airports and train stations. Infiltrated objects represent a very high security threat in critical areas such as airports and train stations. In order to neutralise such a threat, this project will develop new automatic technologies capable of detecting infiltrated objects in sensitive areas in real time, analysing the movements of their original carriers in the nearby areas, and raising attention accordingly. The technologies ....Automatic real-time detection of infiltrated objects for security of airports and train stations. Infiltrated objects represent a very high security threat in critical areas such as airports and train stations. In order to neutralise such a threat, this project will develop new automatic technologies capable of detecting infiltrated objects in sensitive areas in real time, analysing the movements of their original carriers in the nearby areas, and raising attention accordingly. The technologies will be based on the automatic analysis of camera videos made by computers without the need for assessing or storing the identities of common passers-by. The potential of application is huge extending beyond airports and train stations to any public areas.Read moreRead less
Cost efficient scheduling of big data application workflows on cloud through information correlation. Information correlation in and between big data application workflows scheduled on the cloud can help to significantly reduce overall scheduling costs by avoiding the execution of many correlated workflow activities. This project aims to systematically investigate such correlation for cost efficient scheduling. The expected outcomes are: establishing information correlation based scheduling rese ....Cost efficient scheduling of big data application workflows on cloud through information correlation. Information correlation in and between big data application workflows scheduled on the cloud can help to significantly reduce overall scheduling costs by avoiding the execution of many correlated workflow activities. This project aims to systematically investigate such correlation for cost efficient scheduling. The expected outcomes are: establishing information correlation based scheduling research and practical solutions for this important cloud and big data research area; benefiting key big data application areas on the cloud, such as hospitals, insurance companies and government information services; and helping to maintain Australia at the forefront of cloud and big data research with innovative industry applications.Read moreRead less
Integration of Spatiotemporal Video Data for Realtime Smart Proactive Surveillance. This project will have a great impact on the national security by helping the law enforcement agencies to stop crime before it happens. It will automatically detect and tag criminal activities in surveillance videos. It will detect, authenticate, track and profile individuals in sensitive installations. At airports, it will match faces to electronic images embedded in passports. The system will use existing surve ....Integration of Spatiotemporal Video Data for Realtime Smart Proactive Surveillance. This project will have a great impact on the national security by helping the law enforcement agencies to stop crime before it happens. It will automatically detect and tag criminal activities in surveillance videos. It will detect, authenticate, track and profile individuals in sensitive installations. At airports, it will match faces to electronic images embedded in passports. The system will use existing surveillance infrastructures for locating lost people and will also ensure privacy protection of public. On the commercial side, this project can recognize old customers for better and customized services. It can count the number of people present in each floor of a building for rescue operations and for designing future buildings.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE140100007
Funder
Australian Research Council
Funding Amount
$391,947.00
Summary
An Adaptive and Intelligent Service Level Agreement Negotiation System for Web-Based Service-Oriented Grid Computing. This project will develop an intelligent negotiation system for Service Level Agreement (SLA) in web-based service-oriented grid computing. The specific aims include computational models for SLA negotiation representation, intelligent management of SLA negotiation procedures and adaptive learning for SLA negotiation system improvement. The significance of this project lies in its ....An Adaptive and Intelligent Service Level Agreement Negotiation System for Web-Based Service-Oriented Grid Computing. This project will develop an intelligent negotiation system for Service Level Agreement (SLA) in web-based service-oriented grid computing. The specific aims include computational models for SLA negotiation representation, intelligent management of SLA negotiation procedures and adaptive learning for SLA negotiation system improvement. The significance of this project lies in its promises to realise the automation of SLA negotiation through using intelligent and computational models, so as to greatly improve the efficiency of web-based service systems. The research results will enable software engineers to develop more robust and intelligent service-oriented systems through web-based computational grids.Read moreRead less
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
A Computer-Aided Cartooning System. This project is aimed at developing a computer-aided system to accelerate main image-related processes in cartoon production. Using such a system, many of the tedious and repetitive tasks can be performed semi-automatically. The project is focused on accurate representation and matching of shapes. New vectorization methods based on projection onto convex sets (POCS), and new matching methods based on multi-stage hierarchical structures will be developed. The t ....A Computer-Aided Cartooning System. This project is aimed at developing a computer-aided system to accelerate main image-related processes in cartoon production. Using such a system, many of the tedious and repetitive tasks can be performed semi-automatically. The project is focused on accurate representation and matching of shapes. New vectorization methods based on projection onto convex sets (POCS), and new matching methods based on multi-stage hierarchical structures will be developed. The targeted applications include entertainment, next generation mobile services, and the internet.Read moreRead less
A high-speed light-weight embedded vision system for robotics and computer vision applications. Eyesight is the strongest sense for humans and much of the brain is dedicated to vision processing. This project aims to develop an analogous vision capability for small, dynamic robots: a small, light, camera that preprocesses the raw video data to provide higher level information to the robot.