Human gait analysis using SOM

This paper addresses the problem of analysing kinematic gait data which has been collected using 3D motion capture equipment that uses IR-reflective markers place on the joints on the lower extremities of the subject’s body. The data comprises motion trajectories of the different joints and it included normal and pathological subjects. The analysis of motion trajectories is done by combining the wavelet transform for feature extraction and a Kohonen self-organising map (SOM) for classification of walking patterns. Rules are then extracted from the SOM after self-organisation to determine the salient features characterising each cluster. As well as differentiating it from others. It is shown and experimentally verified that salient features do exist within the internal structure of the kinematic data from which diagnostic signatures are elicited. Existence of such features could be used by clinicians in the orthopaedic field.