Artificial intelligence algorithms to predict risk of injury in racehorses. This project will address the urgent need for predicting and preventing catastrophic and career limiting limb injuries and cardiac arrhythmias in racehorses due to over (or under) training. Using data from GPS and movement sensors integrated into saddlecloths, artificial intelligence algorithms will convert cumulative data on speed, gait, and stride characteristics during training, along with injury data, into a risk mat ....Artificial intelligence algorithms to predict risk of injury in racehorses. This project will address the urgent need for predicting and preventing catastrophic and career limiting limb injuries and cardiac arrhythmias in racehorses due to over (or under) training. Using data from GPS and movement sensors integrated into saddlecloths, artificial intelligence algorithms will convert cumulative data on speed, gait, and stride characteristics during training, along with injury data, into a risk matrix. Recorded heart rate and ECG data will also be analysed using artificial intelligence to detect early evidence of the development of cardiac arrhythmias. The system will improve racehorse welfare, providing a simple interface to warn trainers when risk of injury becomes high, in order to prevent catastrophic breakdown.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE170101132
Funder
Australian Research Council
Funding Amount
$372,000.00
Summary
How social relationships improve sheep productivity. This project aims to determine how the social network structure of a flock and different individuals’ experience and leadership abilities improve a population’s well-being and productivity (wool clip and lambing rates). This project will use social network theory and collective behaviour in animals to manage sheep in Australia’s arid rangelands, which are important for the pastoral industry, but where ecological challenges reduce livestock pro ....How social relationships improve sheep productivity. This project aims to determine how the social network structure of a flock and different individuals’ experience and leadership abilities improve a population’s well-being and productivity (wool clip and lambing rates). This project will use social network theory and collective behaviour in animals to manage sheep in Australia’s arid rangelands, which are important for the pastoral industry, but where ecological challenges reduce livestock productivity. An expected outcome is management guidelines for the sheep industry to improve wool and meat production.Read moreRead less