Risk-aware business process management. Risk-aware business process management will revolutionise the identification and treatment of risks in business processes by integrating the latest technologies for risk management and process management. It will provide organisations with a range of new tools and techniques for designing, deploying and monitoring risk-aware business processes.
Cost-aware business process management. The project aims to inform business process management (BPM) with the latest insights from the field of management accounting in order to make BPM systems cost-aware. By incorporating the cost dimension, organisations can obtain an accurate and immediate overview of the true cost of their processes and make cost-informed decisions.
Discovery Early Career Researcher Award - Grant ID: DE210100160
Funder
Australian Research Council
Funding Amount
$423,000.00
Summary
Information Extraction from Large-scale Low-quality Data. Information extraction which identifies entities and relations from data is a key technology that lays the foundation for understanding the semantics of data. This project aims to investigate the problem of information extraction by innovatively exploring the informality and temporal evolution of data. It expects to develop novel techniques for reliable, efficient, and scalable information discovery from large-scale low-quality data. Expe ....Information Extraction from Large-scale Low-quality Data. Information extraction which identifies entities and relations from data is a key technology that lays the foundation for understanding the semantics of data. This project aims to investigate the problem of information extraction by innovatively exploring the informality and temporal evolution of data. It expects to develop novel techniques for reliable, efficient, and scalable information discovery from large-scale low-quality data. Expected outcomes include a set of collective, contextualised, and temporal-aware algorithms for information extraction and integration, built on top of effective indexing and in-parallel processing. This project is anticipated to benefit a considerable number of data-driven intelligence-based applications.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE140100215
Funder
Australian Research Council
Funding Amount
$394,752.00
Summary
Searching Activity Trajectories for Intention Oriented Recommendations. The ubiquitous fusion of social network services and Global Positioning System-enabled mobile devices has generated large-scale activity trajectory data representing the footprint of people's daily activities. It presents an unprecedented opportunity to build highly intelligent recommendation systems. Existing approaches that merely focus on the location aspect of trajectories are limited in their ability to understand genui ....Searching Activity Trajectories for Intention Oriented Recommendations. The ubiquitous fusion of social network services and Global Positioning System-enabled mobile devices has generated large-scale activity trajectory data representing the footprint of people's daily activities. It presents an unprecedented opportunity to build highly intelligent recommendation systems. Existing approaches that merely focus on the location aspect of trajectories are limited in their ability to understand genuine preferences from travel histories, due to lack of consideration for activity information as well as the associated semantics and context. This project aims to address these issues and provide effective recommendations by considering both users’ intention and collective behavioural knowledge inferred from activity trajectories.Read moreRead less
Developing Adversary-Aware Classifiers for Android Malware Detection. Smartphones have become increasingly ubiquitous in people’s everyday life. However, it was reported that one in every five Android applications were actually malware, considering that Android has taken 88% market share of mobile phones. As an effective technique, machine learning has been widely adopted to detect Android malware. However, recent work suggests that deliberately-crafted malware makes machine learning ineffective ....Developing Adversary-Aware Classifiers for Android Malware Detection. Smartphones have become increasingly ubiquitous in people’s everyday life. However, it was reported that one in every five Android applications were actually malware, considering that Android has taken 88% market share of mobile phones. As an effective technique, machine learning has been widely adopted to detect Android malware. However, recent work suggests that deliberately-crafted malware makes machine learning ineffective. In this project, we propose to develop a series of new techniques, such as 1) Android contextual analysis, 2) wrapper-based hill climbing algorithm, and 3) ensemble learning, to solve this problem. The outcomes will help Australia gain cutting edge technologies in adversarial machine learning and mobile security.Read moreRead less
Privacy-Preserving Classification for Big-Data Driven Network Traffic. Protecting sensitive information in large network traffic flows while ensuring data usability for classification emerges as a critical problem of increasing significance. Existing techniques do not work on highly heterogeneous traffic from big-data applications for both privacy protection and classification (such as port-based and load- based methods). This project investigates new theories, methods and techniques for solving ....Privacy-Preserving Classification for Big-Data Driven Network Traffic. Protecting sensitive information in large network traffic flows while ensuring data usability for classification emerges as a critical problem of increasing significance. Existing techniques do not work on highly heterogeneous traffic from big-data applications for both privacy protection and classification (such as port-based and load- based methods). This project investigates new theories, methods and techniques for solving this problem. It proposes to develop a set of effective methods for privacy-preserving data publication through combining randomisation with anonymisation, and for classifying the published data through uncertainty leveraging by probabilistic reasoning and accuracy lifting by inter-flow correlation analysis and active learning.Read moreRead less
Reputation-based trust management in crowdsourcing environments. This project aims to address the critical need for enabling trustworthy crowd sourcing environments. Expected outcomes include innovative solutions to evaluate the reputation and expertise portfolio of workers and identify malicious workers, with the ultimate goal of making personalised recommendations of trustworthy workers with expertise to the requesters who have published tasks. This project is expected to provide key solutions ....Reputation-based trust management in crowdsourcing environments. This project aims to address the critical need for enabling trustworthy crowd sourcing environments. Expected outcomes include innovative solutions to evaluate the reputation and expertise portfolio of workers and identify malicious workers, with the ultimate goal of making personalised recommendations of trustworthy workers with expertise to the requesters who have published tasks. This project is expected to provide key solutions to globally leading crowd sourcing platforms originating in Australia and benefit Australian and worldwide Internet users.Read moreRead less
Detecting Firmware Vulnerabilities in Smart Home Devices. 83% of Australians have smart home devices. 47% claim they have three or more. These devices are easily targeted by cyber-attacks, and searching for their vulnerabilities has become more crucial than ever. Our industry partner GPG is actively looking for ways to detect vulnerabilities in their smart home products, but have not found any existing methods that satisfy three critical requirements: 1) massive search, 2) cross platform detecti ....Detecting Firmware Vulnerabilities in Smart Home Devices. 83% of Australians have smart home devices. 47% claim they have three or more. These devices are easily targeted by cyber-attacks, and searching for their vulnerabilities has become more crucial than ever. Our industry partner GPG is actively looking for ways to detect vulnerabilities in their smart home products, but have not found any existing methods that satisfy three critical requirements: 1) massive search, 2) cross platform detection, and 3) finding unseen vulnerabilities. We therefore propose to use a series of new techniques such as efficient in-memory fuzzing, conditional formulas, and transfer learning to solve the above challenges. The project outcomes will help Australia gain cutting edge techniques in vulnerability detection. Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160100308
Funder
Australian Research Council
Funding Amount
$300,000.00
Summary
Mobile User Modeling for Intelligent Recommendation. This project aims to develop effective and efficient techniques to enable individuals, business and government to better understand and exploit knowledge in human daily activity data and to provide higher quality mobile recommendation services such as personalised trip planning and tourist services. The project intends to develop a mobile user modelling framework which accurately infers mobile users' location-time-dependent interests and spa ....Mobile User Modeling for Intelligent Recommendation. This project aims to develop effective and efficient techniques to enable individuals, business and government to better understand and exploit knowledge in human daily activity data and to provide higher quality mobile recommendation services such as personalised trip planning and tourist services. The project intends to develop a mobile user modelling framework which accurately infers mobile users' location-time-dependent interests and spatial mobility patterns from their daily activity records and social ties in geo-social networks. It then intends to combine this knowledge to build an intelligent recommender system. The project outcomes and techniques could be applied in various location-based services, mobile advertising and marketing.Read moreRead less
Understanding the impact of enterprise system use on system performance. To optimise organizational benefits, resource intensive enterprise systems must be appropriately used by all user cohorts. This study investigates the impact of system-use on system success. System-use patterns derived for all key user cohorts across the lifecycle phases will create management matrices to assist organizations maximise system-use.