The Open Automation and Control Systems Journal

2014, 6 : 108-116
Published online 2014 July 25. DOI: 10.2174/1874444301406010108
Publisher ID: TOAUTOCJ-6-108

Analysis of Extracted Forearm sEMG Signal Using LDA, QDA, K-NN Classification Algorithms

Firas AlOmari and Gunhai Liu
Jiangsu University-School of Electrical and Information Engineering, Xuefu Rd 301#, Zhenjiang 212013, PR China.

ABSTRACT

A surface electromyographic (sEMG) signal includes important information on muscular activity and was recently widely used as an input signal in a myoelectric control system. In this manuscript, eight hand motions were classified using different extracted features from sEMG signals. The results of the experiment show that the combination of sample entropy (SampEnt), root mean square (RMS), myopulse percentage rate (MYOP), and difference absolute standard deviation value (DASDV) achieved the highest classification rate of 98.56% using the linear discriminant analysis (LDA) classifier. Moreover, this study investigated the best value of K that should be used as an input parameter in the K-nearest neighbor (K-NN) algorithm. The result demonstrates that k = 5 is the optimal choice in most cases.

Keywords:

EMG, feature extraction, human-machine interface.