EMG Feature Selection And Classification Using A Pbest-Guide Binary Particle Swarm Optimization

Too, Jing Wei and Tee, Wei Hown and Abdullah, Abdul Rahim and Mohd Saad, Norhashimah (2019) EMG Feature Selection And Classification Using A Pbest-Guide Binary Particle Swarm Optimization. Computation, 7 (1). 02-20. ISSN 2079-3197

Text 2019 EMG FEATURE SELECTION AND CLASSIFICATION USING A PBEST-GUIDE BINARY PARTICLE SWARM OPTIMIZATION.PDF Download (2MB)

Abstract

Due to the increment in hand motion types, electromyography (EMG) features are increasingly required for accurate EMG signals classification. However, increasing in the number of EMG features not only degrades classification performance, but also increases the complexity of the classifier. Feature selection is an effective process for eliminating redundant and irrelevant features. In this paper, we propose a new personal best (Pbest) guide binary particle swarm optimization (PBPSO) to solve the feature selection problem for EMG signal classification. First, the discrete wavelet transform (DWT) decomposes the signal into multiresolution coefficients. The features are then extracted from each coefficient to form the feature vector. After which pbest-guide binary particle swarm optimization (PBPSO) is used to evaluate the most informative features from the original feature set. In order to measure the effectiveness of PBPSO, binary particle swarm optimization (BPSO), genetic algorithm (GA), modified binary tree growth algorithm (MBTGA), and binary differential evolution (BDE) were used for performance comparison. Our experimental results show the superiority of PBPSO over other methods, especially in feature reduction; where it can reduce more than 90% of features while keeping a very high classification accuracy. Hence, PBPSO is more appropriate for application in clinical and rehabilitation applications.

Item Type:	Article
Uncontrolled Keywords:	Binary differential evolution, Binary particle swarm optimization, Classification, Discrete wavelet transform, Electromyography, Feature selection, Genetic algorithm, Particle Swarm Optimization
Divisions:	Faculty of Electrical Engineering
Depositing User:	Sabariah Ismail
Date Deposited:	08 Dec 2020 14:24
Last Modified:	08 Dec 2020 14:24
URI:	http://eprints.utem.edu.my/id/eprint/24627
Statistic Details:	View Download Statistic

Actions (login required)

View Item