Loading [MathJax]/extensions/TeX/cancel.js
sEMG-based continuous hand gesture recognition using GMM-HMM and threshold model | IEEE Conference Publication | IEEE Xplore

sEMG-based continuous hand gesture recognition using GMM-HMM and threshold model


Abstract:

To detect the person's intention for the control of upper-limb exoskeleton robot, we propose a recognition frame of continuous hand gestures. This frame is mainly concent...Show More

Abstract:

To detect the person's intention for the control of upper-limb exoskeleton robot, we propose a recognition frame of continuous hand gestures. This frame is mainly concentrated on dynamic segmentation and real time gesture recognition based on sEMG. The hand gesture was modeled and decomposed by the use of Gaussian Mixture Model-Hidden Markov Models (GMM-HMM). GMMs are employed as a sub-states of HMMs to decode sEMG feature of gesture. The log-likelihood threshold and KL-divergence threshold are adopted to select target gesture model. In myoelectric control schemes, the sEMG data are collected by Myo armband 8-channels sEMG sensors. The proposed framework has ideal classification accuracy and its simpler acquisition armband make it attractive to a real-time myoelectric control system.
Date of Conference: 05-08 December 2017
Date Added to IEEE Xplore: 26 March 2018
ISBN Information:
Conference Location: Macau, Macao

I. Introduction

The surface electromyography (sEMG) signal contains useful information about motion intension that is extensively used for control of the prosthetic hand. However, sEMG signal is a semi-stochastic signal whose dynamic changing process is influenced by anatomical and physiological properties of the contracting muscle [1]. Furthermore, there would be other factors that have impacts on the sEMG signals. Firstly, sEMG sensors with different placements and contact conditions might collect the distinct signals. Secondly, kinetic differences between different individuals when perform the same hand gesture might result in vague corresponding relationship between sEMG and hand gesture [2]. Thirdly, due to muscles collaboration or interaction together during dynamic contractions, coordinated activation of groups of muscles might be non-stationary [3].

References

References is not available for this document.