Three-way analysis of spectrospatial electromyography data: Classification and interpretation

Jukka Pekka Kauppi, Janne Hahne, Klaus Muller, Aapo Hyvärinen

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.

Original languageEnglish
Article numbere0127231
JournalPLoS One
Volume10
Issue number6
DOIs
Publication statusPublished - 2015 Jun 3

Fingerprint

Electromyography
electromyography
hands
Hand
Fingers
prostheses
artificial intelligence
Physiology
Independent component analysis
Prostheses and Implants
sensors (equipment)
Learning systems
Classifiers
physiology
methodology
Technology
Sensors

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Three-way analysis of spectrospatial electromyography data : Classification and interpretation. / Kauppi, Jukka Pekka; Hahne, Janne; Muller, Klaus; Hyvärinen, Aapo.

In: PLoS One, Vol. 10, No. 6, e0127231, 03.06.2015.

Research output: Contribution to journalArticle

Kauppi, Jukka Pekka ; Hahne, Janne ; Muller, Klaus ; Hyvärinen, Aapo. / Three-way analysis of spectrospatial electromyography data : Classification and interpretation. In: PLoS One. 2015 ; Vol. 10, No. 6.
@article{1b9b414133c648ee802d29e2324576e0,
title = "Three-way analysis of spectrospatial electromyography data: Classification and interpretation",
abstract = "Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.",
author = "Kauppi, {Jukka Pekka} and Janne Hahne and Klaus Muller and Aapo Hyv{\"a}rinen",
year = "2015",
month = "6",
day = "3",
doi = "10.1371/journal.pone.0127231",
language = "English",
volume = "10",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "6",

}

TY - JOUR

T1 - Three-way analysis of spectrospatial electromyography data

T2 - Classification and interpretation

AU - Kauppi, Jukka Pekka

AU - Hahne, Janne

AU - Muller, Klaus

AU - Hyvärinen, Aapo

PY - 2015/6/3

Y1 - 2015/6/3

N2 - Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.

AB - Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.

UR - http://www.scopus.com/inward/record.url?scp=84934989388&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84934989388&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0127231

DO - 10.1371/journal.pone.0127231

M3 - Article

C2 - 26039100

AN - SCOPUS:84934989388

VL - 10

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 6

M1 - e0127231

ER -