EMG Pattern Recognition System Based on Neural Networks

Author

Gonzalez-Ibarra, Juan Carlos ; Soubervielle-Montalvo, Carlos ; Vital-Ochoa, Omar ; Perez-Gonzalez, Hector Gerardo

Author_Institution

Centro de Investig. y Estudios de Posgrado (CIEP), Univ. Autonoma de San Luis Potosi (UASLP), San Luis Potosí, Mexico

fYear

2012

fDate

Oct. 27 2012-Nov. 4 2012

Firstpage

71

Lastpage

74

Abstract

In this document we present a methodology for movement pattern recognition from arm-forearm myoelectric signals, starting off from the design and implementation of an electromyography (EMG) instrumentation system, considering the Surface EMG for the Non Invasive Assessment of Muscles (SENIAM) rules. Signal processing and characterization techniques were applied using the pass-band Butter worth digital filter and fast Fourier transform (FFT). Artificial neural networks (ANN) such as back propagation and radial basis function (RBF) were used for the pattern recognition or classification of the EMG signals. The best results were obtained using the RBF ANN, achieving an average accuracy of 98%.

Keywords

Butterworth filters; backpropagation; band-pass filters; digital filters; electromyography; fast Fourier transforms; handicapped aids; medical signal processing; pattern classification; radial basis function networks; signal classification; EMG pattern recognition system; EMG signals; FFT; RBF ANN; SENIAM rules; arm-forearm myoelectric signals; artificial neural networks; back propagation; electromyography instrumentation system; fast Fourier transform; man-machine interface; motor disabilities; movement pattern recognition; pass-band Butter worth digital filter; pattern classification; radial basis function; signal characterization technique; signal processing technique; surface EMG non invasive assessment-of-muscles rules; Accuracy; Artificial neural networks; Electrodes; Electromyography; Muscles; Neurons; Pattern recognition; Artificial Neural Networks; EMG; FFT; Pattern Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Artificial Intelligence (MICAI), 2012 11th Mexican International Conference on

Conference_Location

San Luis Potosi

Print_ISBN

978-1-4673-4731-0

Type

conf

DOI

10.1109/MICAI.2012.23

Filename

6387218