When mathematics and statistics are applied to real world challenges, they have the potential to innovate technologies, optimise systems and understand complexities. The projects below show the breadth of real world challenges that ACEMS has worked on and how mathematics and statistics can both benefit society and contribute to a businesses bottom line.
Also see also ACEMS Research Themes for our technical research projects or join our Industry Affiliate Program to keep to date with the latest news.
Understanding Balance in Training Australia's Elite Athletes
In collaborations with the Australian Institute of Sport, we developed predictive models of athlete performance using the countermovement jump to characterise fatigue as a tool to support coaches and decision makers to optimise training.
Machine Learning & Image Analysis for Grading Rib Eye Fillets
ACEMS PhD student Zoe van Havre worked with the Australia Agricultural Company (AACo) to utilise machine learning and image processing to automatically grade rib eyes.
Optimising Cattle Stocking Decisions
Working with the Australian Agricutlural Company (AACo), ACEMS utilised predictive modelling to predict the weight gain and meat quality of Australian cattle. An important insight that has enabled more informed stocking management decisions.
National Cancer Atlas
ACEMS is working with the Cancer Council Queensland to develop the National Cancer Atlas, which will use cutting edge spatial statistical methods to map how the burden of cancer varies geographically across Australia. A key focus of the Atlas is to develop statistical spatial models for the small counts in each of the geographical areas, while also providing measures of uncertainty around the modelled estimates.
Innovation in Traffic Modeling
CEASAR (Cellular Automata Simulator) is an innovative traffic modelling simulator developed in collaboration with VicRoads. The simulator incorporates realistic traffic signal systems, such as the Sydney Coordinated Adaptive Traffic System (SCATS), and enables dynamic traffic modelling that informs more appropriate traffic signal scheduling.