Towards equity in crash protection. Women are at increased relative risk for death and serious injury in motor vehicle crashes compared to men and the reasons for this are not clear. This Fellowship aims to build a new model that describes the mechanistic pathways for this inequity to identify where and how intervention could reduce this relative risk. This will establish what population groups have good and poor access to the best vehicle safety technologies, the differences, and what might cau ....Towards equity in crash protection. Women are at increased relative risk for death and serious injury in motor vehicle crashes compared to men and the reasons for this are not clear. This Fellowship aims to build a new model that describes the mechanistic pathways for this inequity to identify where and how intervention could reduce this relative risk. This will establish what population groups have good and poor access to the best vehicle safety technologies, the differences, and what might cause these differences in the benefits of vehicle safety technology between women and men. The outcomes will be of use to academics, policy makers and industry designing to new ways to protect women in crashes and close this gender gap.Read moreRead less
AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing n ....AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing novel deep learning algorithms. The new algorithms will benefit a wide range of applications, e.g. to effectively use car crash training samples for accurately identifying potential road crashes in transport and to effectively use rare medical imaging training data for robustly diagnosing diseases in health.Read moreRead less
Advancing cycling as an active transport mode using data driven approaches. This research program aims to provide the critical evidence that is needed to advance cycling as an active and sustainable mode of transport. Through interdisciplinary research and multi-national collaborations, the program will develop a world-leading data platform that will monitor, inform and evaluate cycling, and use this platform to provide the evidence that is needed to enhance cycling participation, safety and inf ....Advancing cycling as an active transport mode using data driven approaches. This research program aims to provide the critical evidence that is needed to advance cycling as an active and sustainable mode of transport. Through interdisciplinary research and multi-national collaborations, the program will develop a world-leading data platform that will monitor, inform and evaluate cycling, and use this platform to provide the evidence that is needed to enhance cycling participation, safety and infrastructure. The outcomes of the research will revolutionise our ability to implement safe and connected cycling infrastructure in areas of greatest need, leading to reduced injury, greater equity and wider uptake of cycling as a mode of transport, thereby leading to substantial gains in population and environmental health.Read moreRead less
Innovative Data Driven Techniques for Structural Condition Monitoring . Safe and sustainable infrastructure involves the development and application of structural monitoring and assessment techniques for condition evaluation. This project develops an innovative structure condition monitoring approach based on the emerging digital technologies on image processing, data analytics and machine learning techniques, for better infrastructure asset management under operational environment. Expected out ....Innovative Data Driven Techniques for Structural Condition Monitoring . Safe and sustainable infrastructure involves the development and application of structural monitoring and assessment techniques for condition evaluation. This project develops an innovative structure condition monitoring approach based on the emerging digital technologies on image processing, data analytics and machine learning techniques, for better infrastructure asset management under operational environment. Expected outcomes of this project enhance the capacity to conduct the operational monitoring and data interpretation to deliver the best life cycle performance of infrastructure. This project should provide significant benefits to Australia in infrastructure asset management by reducing the interruption of infrastructure operations.Read moreRead less
Robust and Explainable 3D Computer Vision. Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-s ....Robust and Explainable 3D Computer Vision. Computer vision is increasingly relying on deep learning which is fragile, opaque and fails catastrophically without warning. This project aims to address these problems by developing new theory in graph representation of 3D geometric and image data, hierarchical graph simplification and novel modules designed specifically for deep learning over geometric graphs. Using these modules, it aims to design graph convolutional network architectures for self-supervised learning that are robust to failures and provide explainable decisions for object detection and scene segmentation. The outcomes are expected to advance theory in robust deep learning and benefit 3D mapping, surveying, infrastructure monitoring, transport and robotics industries.Read moreRead less
Adapting Automation Transparency to Allow Accurate Use by Humans . The project will conduct the human factors research urgently required to discover how best to make automation in high-risk work settings more transparent and usable by humans. In safety-critical work contexts such as defence and aviation, automated decision aids improve human decision-making. Unfortunately however, catastrophic accidents have occurred because human operators have either not followed correct automated advice, or f ....Adapting Automation Transparency to Allow Accurate Use by Humans . The project will conduct the human factors research urgently required to discover how best to make automation in high-risk work settings more transparent and usable by humans. In safety-critical work contexts such as defence and aviation, automated decision aids improve human decision-making. Unfortunately however, catastrophic accidents have occurred because human operators have either not followed correct automated advice, or followed incorrect automated advice. A series of human factors studies using unmanned vehicle control, air traffic control, and submarine track management tasks (including testing experts in field settings) will discover how best to design transparent automation that can be safely and efficiently used by humans.Read moreRead less
Modular microfluidic platform for mimicking multi-organ system interactions. This project aims to develop a novel, modular microfluidic platform that overcomes current limitations of integrated systems in synchronising multi-tissue culture, imaging and operational complexity. Understanding multi-organ systemic crosstalk in human health and diseases demands dynamic culture systems that can mimic such interactions. This project will deliver a first-in-class platform technology and establish intern ....Modular microfluidic platform for mimicking multi-organ system interactions. This project aims to develop a novel, modular microfluidic platform that overcomes current limitations of integrated systems in synchronising multi-tissue culture, imaging and operational complexity. Understanding multi-organ systemic crosstalk in human health and diseases demands dynamic culture systems that can mimic such interactions. This project will deliver a first-in-class platform technology and establish international and disciplinary collaborations to develop different tissue and engineering modules relevant to applications in systemic nanotoxicology, drug bioactivation and chronic diseases. This will provide the cornerstone technology to develop a new generation of disease models and therapeutics targeting interaction dysfunctions.Read moreRead less
Detecting and tracking alertness using speech biometrics. Traditional tests for detecting and tracking alertness are limited by their accuracy and inability to be administered without stopping work. This project aims to investigate how speech can be used to monitor changes in performance resulting from sleep deprivation and successive night shifts. The expected outcomes are 1) new knowledge on how sensitive speech and language features are for detecting change in alertness, and 2) development an ....Detecting and tracking alertness using speech biometrics. Traditional tests for detecting and tracking alertness are limited by their accuracy and inability to be administered without stopping work. This project aims to investigate how speech can be used to monitor changes in performance resulting from sleep deprivation and successive night shifts. The expected outcomes are 1) new knowledge on how sensitive speech and language features are for detecting change in alertness, and 2) development and verification of a highly accurate, cost-effective, speech focussed assay capable of detecting impaired alertness from otherwise healthy individuals. The project should benefit the way fitness for duty is tested and provide new methods for safeguarding Australians working in at-risk environments.Read moreRead less