EMG pattern recognition for persons with cervical spinal cord injury

Nitin Seth; Rafaela C.De Freitas; Mitchell Chaulk; Colleen O'Connell; Kevin Englehart; Erik Scheme

doi:10.1109/ICORR.2019.8779450

EMG pattern recognition for persons with cervical spinal cord injury

Nitin Seth, Rafaela C.De Freitas, Mitchell Chaulk, Colleen O'Connell, Kevin Englehart, Erik Scheme

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

Pattern recognition based myoelectric control has been widely explored in the field of prosthetics, but little work has extended to other patient groups. Individuals with neurological injuries such as spinal cord injury may also benefit from more intuitive control that may facilitate more interactive treatments or improved control of functional electrical stimulation (FES) systems or assistive technologies. This work presents a pilot study with 10 individuals with cervical spinal cord injury between A and C on the American Spinal Injury Association Impairment Scale. Subjects attempted to elicit 10 classes of forearm and hand movements while their electromyogram (EMG) was recorded using a cuff of eight electrodes. Various well-known EMG features were evaluated using a linear discriminant analysis classifier, yielding classification error rates as low as 4.3% ± 3.9 across the 10 classes. Reducing the number of classes to five, those required to control a commercial therapeutic FES device, further reduced the error rates to (2.2% ± 4.4). Results from this study provide evidence supporting continued exploration of EMG pattern recognition techniques for use by high-level spinal cord injured populations as a method of intuitive control over interactive FES systems or assistive devices.

Original language	English
Title of host publication	2019 IEEE 16th International Conference on Rehabilitation Robotics, ICORR 2019
Publisher	IEEE Computer Society
Pages	1055-1060
Number of pages	6
ISBN (Electronic)	9781728127552
DOIs	https://doi.org/10.1109/ICORR.2019.8779450
Publication status	Published - Jun 2019
Externally published	Yes
Event	16th IEEE International Conference on Rehabilitation Robotics, ICORR 2019 - Toronto, Canada Duration: Jun 24 2019 → Jun 28 2019

Publication series

Name	IEEE International Conference on Rehabilitation Robotics
Volume	2019-June
ISSN (Print)	1945-7898
ISSN (Electronic)	1945-7901

Conference

Conference	16th IEEE International Conference on Rehabilitation Robotics, ICORR 2019
Country/Territory	Canada
City	Toronto
Period	6/24/19 → 6/28/19

Bibliographical note

Funding Information:
ACKNOWLEDGMENT We thank clinical partners Brenda McAlpine and Shane McCullum for helping to facilitate the study. This work is supported by the New Brunswick Innovation Foundation, and NSERC Discovery Grants 217354-15 and 2014-04920.

Funding Information:
*This worked was supported by the New Brunswick Innovation Foundation and the Natural Science and Engineering Research Council of Canada (NSERC) through Discovery Grants 217354-15 and 2014-04920.

Publisher Copyright:
© 2019 IEEE.

ASJC Scopus Subject Areas

Control and Systems Engineering
Rehabilitation
Electrical and Electronic Engineering

PubMed: MeSH publication types

Journal Article
Research Support, Non-U.S. Gov't

Access to Document

10.1109/ICORR.2019.8779450

Cite this

Seth, N., Freitas, R. C. D., Chaulk, M., O'Connell, C., Englehart, K., & Scheme, E. (2019). EMG pattern recognition for persons with cervical spinal cord injury. In 2019 IEEE 16th International Conference on Rehabilitation Robotics, ICORR 2019 (pp. 1055-1060). Article 8779450 (IEEE International Conference on Rehabilitation Robotics; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/ICORR.2019.8779450

EMG pattern recognition for persons with cervical spinal cord injury. / Seth, Nitin; Freitas, Rafaela C.De; Chaulk, Mitchell et al.
2019 IEEE 16th International Conference on Rehabilitation Robotics, ICORR 2019. IEEE Computer Society, 2019. p. 1055-1060 8779450 (IEEE International Conference on Rehabilitation Robotics; Vol. 2019-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Seth, N, Freitas, RCD, Chaulk, M, O'Connell, C, Englehart, K & Scheme, E 2019, EMG pattern recognition for persons with cervical spinal cord injury. in 2019 IEEE 16th International Conference on Rehabilitation Robotics, ICORR 2019., 8779450, IEEE International Conference on Rehabilitation Robotics, vol. 2019-June, IEEE Computer Society, pp. 1055-1060, 16th IEEE International Conference on Rehabilitation Robotics, ICORR 2019, Toronto, Canada, 6/24/19. https://doi.org/10.1109/ICORR.2019.8779450

@inproceedings{476492d4a95c4158a1c0868088af9ebd,

title = "EMG pattern recognition for persons with cervical spinal cord injury",

abstract = "Pattern recognition based myoelectric control has been widely explored in the field of prosthetics, but little work has extended to other patient groups. Individuals with neurological injuries such as spinal cord injury may also benefit from more intuitive control that may facilitate more interactive treatments or improved control of functional electrical stimulation (FES) systems or assistive technologies. This work presents a pilot study with 10 individuals with cervical spinal cord injury between A and C on the American Spinal Injury Association Impairment Scale. Subjects attempted to elicit 10 classes of forearm and hand movements while their electromyogram (EMG) was recorded using a cuff of eight electrodes. Various well-known EMG features were evaluated using a linear discriminant analysis classifier, yielding classification error rates as low as 4.3% ± 3.9 across the 10 classes. Reducing the number of classes to five, those required to control a commercial therapeutic FES device, further reduced the error rates to (2.2% ± 4.4). Results from this study provide evidence supporting continued exploration of EMG pattern recognition techniques for use by high-level spinal cord injured populations as a method of intuitive control over interactive FES systems or assistive devices.",

author = "Nitin Seth and Freitas, {Rafaela C.De} and Mitchell Chaulk and Colleen O'Connell and Kevin Englehart and Erik Scheme",

note = "Funding Information: ACKNOWLEDGMENT We thank clinical partners Brenda McAlpine and Shane McCullum for helping to facilitate the study. This work is supported by the New Brunswick Innovation Foundation, and NSERC Discovery Grants 217354-15 and 2014-04920. Funding Information: *This worked was supported by the New Brunswick Innovation Foundation and the Natural Science and Engineering Research Council of Canada (NSERC) through Discovery Grants 217354-15 and 2014-04920. Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th IEEE International Conference on Rehabilitation Robotics, ICORR 2019 ; Conference date: 24-06-2019 Through 28-06-2019",

year = "2019",

month = jun,

doi = "10.1109/ICORR.2019.8779450",

language = "English",

series = "IEEE International Conference on Rehabilitation Robotics",

publisher = "IEEE Computer Society",

pages = "1055--1060",

booktitle = "2019 IEEE 16th International Conference on Rehabilitation Robotics, ICORR 2019",

address = "United States",

}

TY - GEN

T1 - EMG pattern recognition for persons with cervical spinal cord injury

AU - Seth, Nitin

AU - Freitas, Rafaela C.De

AU - Chaulk, Mitchell

AU - O'Connell, Colleen

AU - Englehart, Kevin

AU - Scheme, Erik

N1 - Funding Information: ACKNOWLEDGMENT We thank clinical partners Brenda McAlpine and Shane McCullum for helping to facilitate the study. This work is supported by the New Brunswick Innovation Foundation, and NSERC Discovery Grants 217354-15 and 2014-04920. Funding Information: *This worked was supported by the New Brunswick Innovation Foundation and the Natural Science and Engineering Research Council of Canada (NSERC) through Discovery Grants 217354-15 and 2014-04920. Publisher Copyright: © 2019 IEEE.

PY - 2019/6

Y1 - 2019/6

N2 - Pattern recognition based myoelectric control has been widely explored in the field of prosthetics, but little work has extended to other patient groups. Individuals with neurological injuries such as spinal cord injury may also benefit from more intuitive control that may facilitate more interactive treatments or improved control of functional electrical stimulation (FES) systems or assistive technologies. This work presents a pilot study with 10 individuals with cervical spinal cord injury between A and C on the American Spinal Injury Association Impairment Scale. Subjects attempted to elicit 10 classes of forearm and hand movements while their electromyogram (EMG) was recorded using a cuff of eight electrodes. Various well-known EMG features were evaluated using a linear discriminant analysis classifier, yielding classification error rates as low as 4.3% ± 3.9 across the 10 classes. Reducing the number of classes to five, those required to control a commercial therapeutic FES device, further reduced the error rates to (2.2% ± 4.4). Results from this study provide evidence supporting continued exploration of EMG pattern recognition techniques for use by high-level spinal cord injured populations as a method of intuitive control over interactive FES systems or assistive devices.

AB - Pattern recognition based myoelectric control has been widely explored in the field of prosthetics, but little work has extended to other patient groups. Individuals with neurological injuries such as spinal cord injury may also benefit from more intuitive control that may facilitate more interactive treatments or improved control of functional electrical stimulation (FES) systems or assistive technologies. This work presents a pilot study with 10 individuals with cervical spinal cord injury between A and C on the American Spinal Injury Association Impairment Scale. Subjects attempted to elicit 10 classes of forearm and hand movements while their electromyogram (EMG) was recorded using a cuff of eight electrodes. Various well-known EMG features were evaluated using a linear discriminant analysis classifier, yielding classification error rates as low as 4.3% ± 3.9 across the 10 classes. Reducing the number of classes to five, those required to control a commercial therapeutic FES device, further reduced the error rates to (2.2% ± 4.4). Results from this study provide evidence supporting continued exploration of EMG pattern recognition techniques for use by high-level spinal cord injured populations as a method of intuitive control over interactive FES systems or assistive devices.

UR - http://www.scopus.com/inward/record.url?scp=85071156406&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071156406&partnerID=8YFLogxK

U2 - 10.1109/ICORR.2019.8779450

DO - 10.1109/ICORR.2019.8779450

M3 - Conference contribution

C2 - 31374769

AN - SCOPUS:85071156406

T3 - IEEE International Conference on Rehabilitation Robotics

SP - 1055

EP - 1060

BT - 2019 IEEE 16th International Conference on Rehabilitation Robotics, ICORR 2019

PB - IEEE Computer Society

T2 - 16th IEEE International Conference on Rehabilitation Robotics, ICORR 2019

Y2 - 24 June 2019 through 28 June 2019

ER -

EMG pattern recognition for persons with cervical spinal cord injury

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

PubMed: MeSH publication types

Access to Document

Other files and links

Fingerprint

Cite this