Stabilometry is a branch of medicine responsible for the study of balance and postural control in human beings. To do this, it uses devices known as posturographs, which collect data related to people`s balance. In this paper we propose the use of data mining techniques in order to build predictive models based on a number of variables related to the balance of the analysed subjects. The resulting models can be applied as classification tools for sports talent mapping by determining the sport or sporting discipline best suited to young sportspeople depending on balance, as balance plays a key role in many sports activities. According to the results for data on 15 professional basketball players and 18 ice-skaters, the predictive power is 90.91% in the best case (Unilateral Stance Test - Left Leg). This suggests that there is a close relationship between balance and the sport practised by professional sportspeople in our experiments.
© Copyright 2016 Machine Learning and Data Mining for Sports Analytics ECML/PKDD 2016 workshop. Veröffentlicht von Department of Computer Science, KU Leuven. Alle Rechte vorbehalten. / Übersetzt mit https://www.DeepL.com/Translator