Gait recognition based on EMG with different individuals and sample sizes
Authors:
- 29 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4068-4072
Abstract
The electromyography (EMG) has important applications in human gait recognition. Five phases of gait were classified by support vector machine after EMG data de-nosing and feature extraction. The results show that both individual differences and sample sizes have influenced on gait classification accuracy. The work has a certain practical significance in gait recognition.Keywords
This publication has 18 references indexed in Scilit:
- Classification of gait phases from lower limb EMG: Application to exoskeleton orthosis2013
- EMG signals based gait phases recognition using hidden Markov models2010
- Multi-channel surface EMG classification using support vector machines and signal-based wavelet optimizationBiomedical Signal Processing and Control, 2008
- Artificial Lower Limb with Myoelectrical Control Based on Support Vector Machine2006
- An EMG-Controlled Exoskeleton for Hand Rehabilitation2005
- The humanID gait challenge problem: data sets, performance, and analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Evaluation of the forearm EMG signal features for the control of a prosthetic handPhysiological Measurement, 2003
- EMG feature evaluation for movement control of upper extremity prosthesesIEEE Transactions on Rehabilitation Engineering, 1995
- Support-vector networksMachine Learning, 1995
- Singularity detection and processing with waveletsIEEE Transactions on Information Theory, 1992