Gait Type Classification Using Smart Insole Sensors

Abstract

In this paper, we propose a gait type classification method using various sensors in a smart insole. The measured data are normalized to the unit step of the same length in order to reduce the variation of the speed according to the measurement point and the situation even within the same gait type. From the normalized data of the individual sensors, the discriminant features useful for gait type classification are extracted by using the Null-Space Linear Discriminant Analysis (NLDA), one of the representative discriminant analysis methods. As a result of experiments on the data measured for the seven gait types, our method gives a good performance of gait type classification.