Comprehensive data comparison and evaluation of gait features using Principal Component Analysis

Abstract

Recently, principal component analysis (PCA) has attracted increasing interest in biomechanical studies because of its usefulness in identifying the movement characteristics of various groups under various conditions using whole data waveforms. However, previous studies using PCA on the matrix constructed from the data of whole trials failed to separate the inter-subject component and the intra-subject component of gait features in their analysis. Therefore, this study proposed a new method to clear this problem and verified its relevance by comparing the gait features of fallers and non-fallers between the proposed method and the ordinary method. As a result of this study, we found that (1) both methods output similar gait features, but (2) the repeatability of proposed method was much higher than the ordinary method.