Motion analysis systems are widely employed within universities and clinical facilities to identify movement pattern that hamper performance, increase the risk of injury or describe anomalies. Knowing such pattern allows a targeted manipulation of a movement and can improve the outcome of a task in respect to performance, risk of injury and anomaly. However, there is yet little scientific evidence in respect to what a 'normal' movement is or what exercises can highlight movement deficiencies best - e.g. findings across studies are often conflicting (Hewett et al., 2005 & Krosshaug et al., 2016). However, conclusions are commonly based on an analysis that has not changed much over the last decades. To date, most studies still use a discrete point feature extraction examining best or average trail using a magnitude based inference testing. This might explain why studies are so often conflicting. The aim of this paper is to introduce a framework that mathematical reduces movement data in combination with a machine learning technique to examine the ability of a battery of exercises to objectively detect describe anomalies.
© Copyright 2018 Sportinformatik XII. 12. Symposium der dvs-Sektion "Sportinformatik und Sporttechnologie" vom 5.-7. September 2018 in Garching. Abstracts.. Veröffentlicht von Feldhaus, Ed. Czwalina. Alle Rechte vorbehalten.