Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders

• Published in: Computers in biology and medicine Vol. 43; no. 5; pp. 576 - 586
• Main Author: Subasi, Abdulhamit
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2013; Elsevier Limited
• Subjects: Action Potentials; Adolescent; Adult; Algorithms; Child; Classification; Discrete wavelet transform (DWT); electromyography; Electromyography (EMG); Electromyography - instrumentation; Electromyography - methods; Female; Humans; Internal Medicine; k-Nearest neigbour (k-NN); Male; Middle Aged; Motor unit action potentials (MUAPs); Muscular Diseases - diagnosis; Muscular Diseases - physiopathology; Muscular system; Neural networks; neuromuscular disorders; Other; Parameter selection; Particle swarm optimization (PSO); Peripheral Nervous System Diseases - diagnosis; Peripheral Nervous System Diseases - physiopathology; Radial basis function networks (RBFN); Reproducibility of Results; Signal processing; Studies; Support Vector Machine; Support vector machine (SVM); support vector machines; wavelet; Wavelet Analysis; Discrete wavelet transform (DWT); Support vector machine (SVM); Electromyography (EMG); Particle swarm optimization (PSO); Motor unit action potentials (MUAPs); Radial basis function networks (RBFN); k-Nearest neigbour (k-NN); Parameter selection
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2013.01.020

Support vector machine (SVM) is an extensively used machine learning method with many biomedical signal classification applications. In this study, a novel PSO-SVM model has been proposed that hybridized the particle swarm optimization (PSO) and SVM to improve the EMG signal classification accuracy. This optimization mechanism involves kernel parameter setting in the SVM training procedure, which significantly influences the classification accuracy. The experiments were conducted on the basis of EMG signal to classify into normal, neurogenic or myopathic. In the proposed method the EMG signals were decomposed into the frequency sub-bands using discrete wavelet transform (DWT) and a set of statistical features were extracted from these sub-bands to represent the distribution of wavelet coefficients. The obtained results obviously validate the superiority of the SVM method compared to conventional machine learning methods, and suggest that further significant enhancements in terms of classification accuracy can be achieved by the proposed PSO-SVM classification system. The PSO-SVM yielded an overall accuracy of 97.41% on 1200 EMG signals selected from 27 subject records against 96.75%, 95.17% and 94.08% for the SVM, the k-NN and the RBF classifiers, respectively. PSO-SVM is developed as an efficient tool so that various SVMs can be used conveniently as the core of PSO-SVM for diagnosis of neuromuscular disorders.