Header

UZH-Logo

Maintenance Infos

Motor execution detection based on autonomic nervous system responses


Marchal-Crespo, Laura; Zimmermann, Raphael; Lambercy, Olivier; Edelmann, Janis; Fluet, Marie-Christine; Wolf, Martin; Gassert, Roger; Riener, Robert (2013). Motor execution detection based on autonomic nervous system responses. Physiological Measurement, 34(1):35-51.

Abstract

Triggered assistance has been shown to be a successful robotic strategy for provoking motor plasticity, probably because it requires neurologic patients' active participation to initiate a movement involving their impaired limb. Triggered assistance, however, requires sufficient residual motor control to activate the trigger and, thus, is not applicable to individuals with severe neurologic injuries. In these situations, brain and body-computer interfaces have emerged as promising solutions to control robotic devices. In this paper, we investigate the feasibility of a body-machine interface to detect motion execution only monitoring the autonomic nervous system (ANS) response. Four physiological signals were measured (blood pressure, breathing rate, skin conductance response and heart rate) during an isometric pinching task and used to train a classifier based on hidden Markov models. We performed an experiment with six healthy subjects to test the effectiveness of the classifier to detect rest and active pinching periods. The results showed that the movement execution can be accurately classified based only on peripheral autonomic signals, with an accuracy level of 84.5%, sensitivity of 83.8% and specificity of 85.2%. These results are encouraging to perform further research on the use of the ANS response in body-machine interfaces.

Abstract

Triggered assistance has been shown to be a successful robotic strategy for provoking motor plasticity, probably because it requires neurologic patients' active participation to initiate a movement involving their impaired limb. Triggered assistance, however, requires sufficient residual motor control to activate the trigger and, thus, is not applicable to individuals with severe neurologic injuries. In these situations, brain and body-computer interfaces have emerged as promising solutions to control robotic devices. In this paper, we investigate the feasibility of a body-machine interface to detect motion execution only monitoring the autonomic nervous system (ANS) response. Four physiological signals were measured (blood pressure, breathing rate, skin conductance response and heart rate) during an isometric pinching task and used to train a classifier based on hidden Markov models. We performed an experiment with six healthy subjects to test the effectiveness of the classifier to detect rest and active pinching periods. The results showed that the movement execution can be accurately classified based only on peripheral autonomic signals, with an accuracy level of 84.5%, sensitivity of 83.8% and specificity of 85.2%. These results are encouraging to perform further research on the use of the ANS response in body-machine interfaces.

Statistics

Citations

9 citations in Web of Science®
11 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

2 downloads since deposited on 06 Aug 2013
0 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Neonatology
04 Faculty of Medicine > Balgrist University Hospital, Swiss Spinal Cord Injury Center
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:2013
Deposited On:06 Aug 2013 08:15
Last Modified:05 Apr 2016 16:53
Publisher:IOP Publishing
ISSN:0967-3334
Publisher DOI:https://doi.org/10.1088/0967-3334/34/1/35
Official URL:http://iopscience.iop.org/0967-3334/34/1/35/
PubMed ID:23248174

Download

Preview Icon on Download
Content: Published Version
Filetype: PDF - Registered users only
Size: 673kB
View at publisher