ANALYSIS OF HUMAN MOTION WITH METHODS FROM MACHINE LEARNING

Abstract

Usually, predefined kinematic parameters are investigated in biomechanical studies of human motion. In recent years, techniques of machine learning have been added to this field of research (Chau, 2001). In this study different dimension reduction methods like Principal Component Analysis (PCA) and Fourier Transformation (FT) are investigated as an alternative to common biomechanical approaches in motion analysis.