Home // ICCGI 2014, The Ninth International Multi-Conference on Computing in the Global Information Technology // View article
Authors:
Michele Pla Mobarak
Juan Manuel Gutiérrez Salgado
Roberto Muñoz Guerrero
Valérie Louis-Dorr
Keywords: EMG steady state; EMG transient state; Hjorth's parameters; multichannel EMG; normalized slope descriptors
Abstract:
Most myoelectric controlled systems are based on the common assumption that there is no information in the instantaneous value of the myoelectric signal and therefore, analysis is made on the steady state of the muscle contraction. However, this control scheme faces two main drawbacks: users need to be trained in order to produce the sustained contractions, and the control signal can only be generated until the steady state is reached. Prosthetic devices with long actuating delays often result in users’ frustration and eventually, in the abandonment of the devices. As a proposed solution, analysis of the transient state of the electromyography (EMG) signal would allow classifying movements during the dynamic part of the muscle contractions reducing the time required to generate control commands. This paper proposes a novel method for transient EMG classification based on the use of Hjorth’s parameters. Surface multichannel EMG signals were recorded from 10 normally limbed subjects for both the transient and steady EMG states while performing six different hand motions. Comparatively high classification accuracy was obtained from the transient state analysis of the signals suggesting the existence of deterministic information in this part of the muscle contraction and the fact that Hjorth’s parameters seem to adapt well enough to the nature of myoelectric signals as to allow extracting highly representative information from them.
Pages: 24 to 30
Copyright: Copyright (c) IARIA, 2014
Publication date: June 22, 2014
Published in: conference
ISSN: 2308-4529
ISBN: 978-1-61208-346-9
Location: Seville, Spain
Dates: from June 22, 2014 to June 26, 2014