Application of functional principal component analysis in race walking: an emerging methodology

Abstract

This study considered the problem of identifying and evaluating the factors of individual performance during race walking. In particular, the study explored the use of functional principal component analysis (f-PCA), a multivariate data analysis, for assessing and classifying the kinematics and kinetics of the knee joint in competitive race walkers. Seven race walkers of international and national level participated to the study. An optoelectronic system and a force platform were used to capture three-dimensional kinematics and kinetics of lower limbs during the race walking cycle. Functional principal component analysis was applied bilaterally to the sagittal knee angle and net moment data, because knee joint motion is fundamental to race walking technique. Scatterplots of principal component scores provided evidence of athletes' technical differences and asymmetries even when traditional analysis (mean +/- s curves) was not effective. Principal components provided indications for race walkers' classification and identified potentially important technical differences between higher and lower skilled athletes. Therefore, f-PCA might represent a future aid for the fine analysis of sports movements, if consistently applied to performance monitoring.