A novel pre-processing procedure for enhanced feature extraction and characterization of electromyogram signals. (April 2018)

• Record Type: Journal Article
• Authors: Powar, Omkar S.; Chemmangat, Krishnan; Figarado, Sheron
• Is Part Of: Biomedical signal processing and control. Volume 42(2018)
• Page Start: 277
• Page End: 286
• Publication Date: 2018-04
• Subjects: Minimum Entropy Deconvolution -- EMG -- Feature extraction -- Feature selection -- Classification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.02.006
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Pre-processing step, Minimum Entropy Deconvolution (MEDA) applied for sEMG analysis. Study the classification accuracy without and with the pre-processing step using MEDA. After MEDA, removing redundant features and finding the most stable features. Abstract: In the analysis of electromyogram signals, the challenge lies in the suppression of noise associated with the measurement and signal conditioning. The main aim of this paper is to present a novel pre-processing step, namely Minimum Entropy Deconvolution Adjusted (MEDA), to enhance the signal for feature extraction resulting in better characterization of different upper limb motions. MEDA method is based on finding the set of filter coefficients that recover the output signal with maximum value of kurtosis while minimizing the low kurtosis noise components. The proposed method has been validated on surface electromyogram dataset collected from seven subjects performing eight classes of hand movements (wrist flexion, wrist radial deviation, hand close, tripod, wrist extension, wrist ulnar deviation, cylindrical and key grip) with only two pairs of electrodes recorded from flexor carpi radialis and extensor carpi radialis on the forearm. The performance of the MEDA has been compared across four classifiers namely J-48, k-nearest neighbours (KNN), Naives Bayes and Linear Discriminant Analysis (LDA) attaining the classification accuracy of 85.3 ± 4%, 85.67 ± 5%, 76 ± 6% and 91.2 ± 2% respectively. Practical results demonstrate the feasibility of the approach with mean percentage increase in classification accuracy of 20.5%, without significant increase in computational time across seven subjects demonstrating the significance of MEDA in classification.