User-independent hand motion classification with electromyography

Alison E. Gibson, Mark R. Ison, Panagiotis Artemiadis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Electromyographic (EMG) processing is an important research area with direct applications to prosthetics, exoskeletons and human-machine interaction. Current state of the art decoding methods require intensive training on a single user before it can be utilized, and have been unable to achieve both userindependence and real-time performance. This paper presents a real-time EMG classification method which generalizes across users without requiring an additional training phase. An EMGembedded sleeve quickly positions and records from EMG surface electrodes on six forearm muscles. An optimized decision tree classifies signals from these sensors into five distinct movements for any given user using EMG energy synergies between muscles. This method was tested on 10 healthy subjects using leave-one-out validation, resulting in an overall accuracy of 79±6:6%, with sensitivity and specificity averaging 66% and 97.6%, respectively, over all classified motions. The high specificity values demonstrate the ability to generalize across users, presenting opportunities for large-scale studies and broader accessibility to EMG-driven applications.

Original languageEnglish (US)
Title of host publicationASME 2013 Dynamic Systems and Control Conference, DSCC 2013
PublisherAmerican Society of Mechanical Engineers (ASME)
Volume2
ISBN (Print)9780791856130
DOIs
StatePublished - 2013
EventASME 2013 Dynamic Systems and Control Conference, DSCC 2013 - Palo Alto, CA, United States
Duration: Oct 21 2013Oct 23 2013

Other

OtherASME 2013 Dynamic Systems and Control Conference, DSCC 2013
CountryUnited States
CityPalo Alto, CA
Period10/21/1310/23/13

Fingerprint

Electromyography
Muscle
Decision trees
Prosthetics
Decoding
Electrodes
Sensors
Processing

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Gibson, A. E., Ison, M. R., & Artemiadis, P. (2013). User-independent hand motion classification with electromyography. In ASME 2013 Dynamic Systems and Control Conference, DSCC 2013 (Vol. 2). [DSCC2013-3832] American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DSCC2013-3832

User-independent hand motion classification with electromyography. / Gibson, Alison E.; Ison, Mark R.; Artemiadis, Panagiotis.

ASME 2013 Dynamic Systems and Control Conference, DSCC 2013. Vol. 2 American Society of Mechanical Engineers (ASME), 2013. DSCC2013-3832.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gibson, AE, Ison, MR & Artemiadis, P 2013, User-independent hand motion classification with electromyography. in ASME 2013 Dynamic Systems and Control Conference, DSCC 2013. vol. 2, DSCC2013-3832, American Society of Mechanical Engineers (ASME), ASME 2013 Dynamic Systems and Control Conference, DSCC 2013, Palo Alto, CA, United States, 10/21/13. https://doi.org/10.1115/DSCC2013-3832
Gibson AE, Ison MR, Artemiadis P. User-independent hand motion classification with electromyography. In ASME 2013 Dynamic Systems and Control Conference, DSCC 2013. Vol. 2. American Society of Mechanical Engineers (ASME). 2013. DSCC2013-3832 https://doi.org/10.1115/DSCC2013-3832
Gibson, Alison E. ; Ison, Mark R. ; Artemiadis, Panagiotis. / User-independent hand motion classification with electromyography. ASME 2013 Dynamic Systems and Control Conference, DSCC 2013. Vol. 2 American Society of Mechanical Engineers (ASME), 2013.
@inproceedings{c66a91aaee024b1dad82e24af187e9fa,
title = "User-independent hand motion classification with electromyography",
abstract = "Electromyographic (EMG) processing is an important research area with direct applications to prosthetics, exoskeletons and human-machine interaction. Current state of the art decoding methods require intensive training on a single user before it can be utilized, and have been unable to achieve both userindependence and real-time performance. This paper presents a real-time EMG classification method which generalizes across users without requiring an additional training phase. An EMGembedded sleeve quickly positions and records from EMG surface electrodes on six forearm muscles. An optimized decision tree classifies signals from these sensors into five distinct movements for any given user using EMG energy synergies between muscles. This method was tested on 10 healthy subjects using leave-one-out validation, resulting in an overall accuracy of 79±6:6{\%}, with sensitivity and specificity averaging 66{\%} and 97.6{\%}, respectively, over all classified motions. The high specificity values demonstrate the ability to generalize across users, presenting opportunities for large-scale studies and broader accessibility to EMG-driven applications.",
author = "Gibson, {Alison E.} and Ison, {Mark R.} and Panagiotis Artemiadis",
year = "2013",
doi = "10.1115/DSCC2013-3832",
language = "English (US)",
isbn = "9780791856130",
volume = "2",
booktitle = "ASME 2013 Dynamic Systems and Control Conference, DSCC 2013",
publisher = "American Society of Mechanical Engineers (ASME)",

}

TY - GEN

T1 - User-independent hand motion classification with electromyography

AU - Gibson, Alison E.

AU - Ison, Mark R.

AU - Artemiadis, Panagiotis

PY - 2013

Y1 - 2013

N2 - Electromyographic (EMG) processing is an important research area with direct applications to prosthetics, exoskeletons and human-machine interaction. Current state of the art decoding methods require intensive training on a single user before it can be utilized, and have been unable to achieve both userindependence and real-time performance. This paper presents a real-time EMG classification method which generalizes across users without requiring an additional training phase. An EMGembedded sleeve quickly positions and records from EMG surface electrodes on six forearm muscles. An optimized decision tree classifies signals from these sensors into five distinct movements for any given user using EMG energy synergies between muscles. This method was tested on 10 healthy subjects using leave-one-out validation, resulting in an overall accuracy of 79±6:6%, with sensitivity and specificity averaging 66% and 97.6%, respectively, over all classified motions. The high specificity values demonstrate the ability to generalize across users, presenting opportunities for large-scale studies and broader accessibility to EMG-driven applications.

AB - Electromyographic (EMG) processing is an important research area with direct applications to prosthetics, exoskeletons and human-machine interaction. Current state of the art decoding methods require intensive training on a single user before it can be utilized, and have been unable to achieve both userindependence and real-time performance. This paper presents a real-time EMG classification method which generalizes across users without requiring an additional training phase. An EMGembedded sleeve quickly positions and records from EMG surface electrodes on six forearm muscles. An optimized decision tree classifies signals from these sensors into five distinct movements for any given user using EMG energy synergies between muscles. This method was tested on 10 healthy subjects using leave-one-out validation, resulting in an overall accuracy of 79±6:6%, with sensitivity and specificity averaging 66% and 97.6%, respectively, over all classified motions. The high specificity values demonstrate the ability to generalize across users, presenting opportunities for large-scale studies and broader accessibility to EMG-driven applications.

UR - http://www.scopus.com/inward/record.url?scp=84902385179&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902385179&partnerID=8YFLogxK

U2 - 10.1115/DSCC2013-3832

DO - 10.1115/DSCC2013-3832

M3 - Conference contribution

AN - SCOPUS:84902385179

SN - 9780791856130

VL - 2

BT - ASME 2013 Dynamic Systems and Control Conference, DSCC 2013

PB - American Society of Mechanical Engineers (ASME)

ER -