Abstract: In elite sport the recent application of Micro-Electrical-Mechanical devices (MEMs) containing accelerometers and gyroscopes has allowed recording of athlete movement during matches and training. These devices have become common-place to quantify the external workload of athletes over a given time period. Workload, also called Playerload, has become a proxy parameter to assess athlete energy expenditure. However, one area that shows great potential from the data generated from MEM’s devices is the detection and classification of High Intensity Events (HIEs) and locomotion through Human Activity Recognition (HAR).
Success in competitive sport often relies on players making quick, explosive movements. Using netball as a test case this research will use the latest statistical and machine learning techniques to classify and analyse the fine-scale composition of Playerload to define player performance envelops. It is believed this will provide a tool that better represents athletes’ key movements that Playerload alone can’t provide.
We look forward to seeing you there
The Graduate Research Office (email@example.com)