Myoelectric Signal Classification Using A Finite Impulse Response Neural Network

Loading...
Thumbnail Image

Date

1994

Journal Title

Journal ISSN

Volume Title

Repository Usage Stats

272
views
323
downloads

Abstract

Recent work by Hudgins has proposed a neural network-based approach to classifying themyoelectric signal (MES) elicited at the onset of movement of the upper limb. A standard feed forward artificial network was trained (using the backpropagation algorithm) to discriminatearnongst four classes of upper-limb movements from the MES acquired from the biceps and triceps muscles The approach has demonstrated a powerful means of classifying limb function intent from the MES during natural muscular contraction, but the static nature of the network architecture fails to fullycharacterize the dynamic structure inherent in the MES. It has been demonstrated that a finite-impulseresponse (FIR) network has the ability to incorporate the temporal structure of a signal, representing the relationships between events in time and providing translation invariance of the relevant feature set. The application of this network architecture to limb function discrimination from the MES is described here.

Type

Department

Description

Provenance

Citation

From "MEC 94," Proceedings of the 1993 MyoElectric Controls/Powered Prosthetics Symposium Fredericton, New Brunswick, Canada: August, 1994. Copyright University of New Brunswick.

Copyright 2002, 2005 and 2008, The University of New Brunswick.

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License. Creative Commons License