Comparison of adaptive systems for suppression of stimulation artifacts in EMG signals

Author

Barbosa-Mier, Rafael I. ; Chica, Andrés Carrillo ; Riveros, J. Fernando Vega

Author_Institution

Dept. of Electron. Eng., Pontificia Univ. Javeriana, Colombia

fYear

1995

Firstpage

144

Lastpage

148

Abstract

An electromyographic signal (EMG) is formed by a component that is medically useful which contains information about the muscular activity, and an artifact, which is caused by external effects, e.g., Functional Electrical Stimulation (FES) signals. Several methods have been used to suppress such artifacts based on adaptive schemes. This paper presents a comparison between an adaptive filter using the Least Mean Squares algorithm (LMS) and a Multilayer Perceptron (MLP) using error Backpropagation (BP), Recursive Least Squares (RLS) and Iterative Least Squares (ILS) algorithms. The criteria for comparison are artifact suppression and speed of convergence

Keywords

adaptive filters; backpropagation; electromyography; iterative methods; least mean squares methods; least squares approximations; medical signal processing; multilayer perceptrons; EMG signal; FES signal; adaptive filter; convergence; electromyography; error backpropagation; functional electrical stimulation; iterative least squares algorithm; least mean squares algorithm; multilayer perceptron; muscular activity; recursive least squares algorithm; stimulation artifact suppression; Adaptive filters; Adaptive systems; Backpropagation; Electromyography; Least mean square algorithms; Least squares approximation; Least squares methods; Multilayer perceptrons; Neuromuscular stimulation; Resonance light scattering;

fLanguage

English

Publisher

ieee

Conference_Titel

Devices, Circuits and Systems, 1995., Proceedings of the 1995 First IEEE International Caracas Conference on

Conference_Location

Caracas

Print_ISBN

0-7803-2672-5

Type

conf

DOI

10.1109/ICCDCS.1995.499133

Filename

499133