Seasonal adjustment using disaggregated short time span data. Seasonally adjusted economic and social times series are vital information used by governments and businesses in decision making. This project will develop statistical methods to estimate and remove seasonal factors from economic and social time series using finely disaggregated data for a relatively small number of time periods. This will enable better and quicker estimation of seasonal factors when new series are introduced or there ....Seasonal adjustment using disaggregated short time span data. Seasonally adjusted economic and social times series are vital information used by governments and businesses in decision making. This project will develop statistical methods to estimate and remove seasonal factors from economic and social time series using finely disaggregated data for a relatively small number of time periods. This will enable better and quicker estimation of seasonal factors when new series are introduced or there a major changes to existing series, improving the analysis of such series and the decisions based on them.Read moreRead less
Developing Interpretable Machine Learning Models For Clinical Imaging And Single-cell Genomics
Funder
National Health and Medical Research Council
Funding Amount
$1,312,250.00
Summary
Machine learning methods will be vital to make best use of the deluge of data generated by high-throughput technologies in biomedical science. To get the most out of these models, however, we need to be able to unpack the 'black box'. I will use curated clinical and public research data to benchmark and develop interpretable deep learning models and software tools. These models will be used for breast cancer screening programs and for analysis of complex, large-scale single-cell genomics data.
New statistical tools for mineral exploration targeting and validation. Exploration for new mineral resources depends on information gleaned from geological survey data. This project confronts important, unsolved statistical problems in the analysis of geological survey data which have direct impact on exploration targeting.
Judges' work, place and psychological health - a national view. This project aims to address the human, juridical and financial costs of judicial officers’ work-related psychological harm. This harm is implicated in early retirement, sick leave and suicide. It threatens appropriate courtroom conduct, procedural fairness and impartial adjudication. The project seeks to generate new knowledge of the stress judicial officers experience and the individual and institutional mechanisms for managing st ....Judges' work, place and psychological health - a national view. This project aims to address the human, juridical and financial costs of judicial officers’ work-related psychological harm. This harm is implicated in early retirement, sick leave and suicide. It threatens appropriate courtroom conduct, procedural fairness and impartial adjudication. The project seeks to generate new knowledge of the stress judicial officers experience and the individual and institutional mechanisms for managing stressors, combining socio-legal and psychological approaches. Expected outcomes include evidence-based understandings to inform recruitment and retention strategies specific to this highly specialized workforce. This should provide significant benefits for judges’ work capacities and courts' delivery of justice.Read moreRead less
Creating perceptual experts in Australia's policing and security agencies. This project aims to create the next generation of experts in Australia’s policing and national security agencies, by improving crime scene evidence interpretation. Agencies are under pressure to develop more rigorous training practices that go beyond mere intuition and tradition. This project will use a novel approach that directs learning toward the most diagnostic perceptual cues. Expected outcomes include a solid empi ....Creating perceptual experts in Australia's policing and security agencies. This project aims to create the next generation of experts in Australia’s policing and national security agencies, by improving crime scene evidence interpretation. Agencies are under pressure to develop more rigorous training practices that go beyond mere intuition and tradition. This project will use a novel approach that directs learning toward the most diagnostic perceptual cues. Expected outcomes include a solid empirical basis for national training programs designed to create experts that are accurate, reliable, and continuously improving. Improving the training of experts will ensure the integrity of forensics as evidentiary tools available to police, lead to more reliable courtroom convictions and help safeguard Australia from terrorism and crime.Read moreRead less
Aboriginal and non-Aboriginal sex-offenders in Australia: Assessing risk for practice and policy. A key priority of Australian governments is to improve community safety through reducing the risk of sex offenders re-offending after release from prison. This project will assess the validity of tools used to predict the risk of sexual offender recidivism and identify alternate risk assessment tools for Indigenous and non-Indigenous sex offenders.
A formal signal detection model of eyewitness identification. The project aims to aid in producing better procedures for the collection and assessment of eyewitness identification evidence. In a police line-up, a witness is asked to identify a perpetrator from a group of similar individuals. Applied research has focused on conditions that optimise witness performance but many of the conclusions from this research have been challenged on the basis that they use inappropriate measures of performan ....A formal signal detection model of eyewitness identification. The project aims to aid in producing better procedures for the collection and assessment of eyewitness identification evidence. In a police line-up, a witness is asked to identify a perpetrator from a group of similar individuals. Applied research has focused on conditions that optimise witness performance but many of the conclusions from this research have been challenged on the basis that they use inappropriate measures of performance. Recent work has highlighted the usefulness of analyses based on the theory of signal detection. However, the line-up task does not fit easily within standard signal detection paradigms as it combines two tasks; detection and identification. The project aims to understand how these components work in order to measure witness performance.Read moreRead less
Industrial Transformation Training Centres - Grant ID: IC190100031
Funder
Australian Research Council
Funding Amount
$3,973,202.00
Summary
ARC Training Centre in Data Analytics for Resources and Environments (DARE). Understanding the cumulative impact of actions regarding the use of our resources has important long-term consequences for Australia’s economic, societal and environmental health. Yet despite the importance of these cumulative impacts, and the availability of data, many decisions and policies are based on limited amounts of data and rudimentary data analysis, with little appreciation of the critical role that understand ....ARC Training Centre in Data Analytics for Resources and Environments (DARE). Understanding the cumulative impact of actions regarding the use of our resources has important long-term consequences for Australia’s economic, societal and environmental health. Yet despite the importance of these cumulative impacts, and the availability of data, many decisions and policies are based on limited amounts of data and rudimentary data analysis, with little appreciation of the critical role that understanding and quantifying uncertainty plays in the process. The aim of Data Analytics in Resources and Environment (DARE) is to develop and deliver the data science skills and tools for Australia’s resource industries to make the best possible evidence-based decisions in exploiting and stewarding the nation’s natural resources.Read moreRead less
Statistical methodology for events on a network, with application to road safety. This project develops new methods to analyse road traffic accident rates, aiming to identify accident black spots and to develop an evidence base for future road design and road safety management. These methods can be applied to other types of events on a network of roads, railways, rivers, electrical wires, communication networks or airline routes.
Towards a safer workplace: promoting healthy work environments through strategic research in memory and behaviour change. In collaboration with WorkCover NSW, psychologists plan to develop new strategies to promote healthy and safe work environments. The researchers will find how to: best motivate people to engage in healthy work practices and obtain comprehensive and accurate information about the causes of accidents.