Gait Recognition Based on EMG Information with Multiple Features

Yueying Cao,Qingshan She,Liling Yu,Farong Gao

doi:10.1007/978-3-030-00828-4_41

Abstract

In order to evaluate the effects of time domain (TD) and frequency domain (FD) features as well as muscle number on gait classification recognition, eight channels of electromyography (EMG) signals were collected from four thigh and four lower leg muscles, and two TD features and two FD features were extracted in this study. The method of support vector machine (SVM) was presented to investigate the classification property. For the classification stability and accuracy, 3-fold cross validation was verified and selected to classify the lower limb gait. The results show that the FD features can obtain higher accuracy than TD features. In addition, accuracy of gait recognition increased with the augment of muscle number.

Highlights

IntroductionGait is a dynamic and successive activity achieved through the movement of limbs while daily walking
Normal human gait has the characteristics of coordination, proportionality and periodicity
Based on the results of four groups of experimental data, we found that the effects of muscle number augment on gait recognition rates are greater than that of feature number increasing

Summary

Introduction

Gait is a dynamic and successive activity achieved through the movement of limbs while daily walking. Normal human gait has the characteristics of coordination, proportionality and periodicity. According to the toe-off and heel-strike, an integrated gait cycle can be basically divided into two gait phases, the swing phase and the stand phase [1]. Gait analysis is the powerful tool of walking function in the areas of sports science, rehabilitation therapy and clinical assessment. Santilli et al examined fourteen athletes with functional ankle instability during gait cycle [2]. Bogataj presented an aggressive approach to gait relearning in patients who were unable to walk independently with hemiplegia by means of multichannel functional electrical stimulation combined with conventional therapy [3]. Fish et al provided a clinical assessment of the gait which may be used to monitor the value of physiotherapy treatment for people who have neurological deficits [4]

Methods

Results

Discussion

Conclusion