An artificial EMG generation model based on signal-dependent noise and related application to motion classification

Akira Furui, Hideaki Hayashi, Go Nakamura, Takaaki Chin, Toshio Tsuji

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper proposes an artificial electromyogram (EMG) signal generation model based on signal-dependent noise, which has been ignored in existing methods, by introducing the stochastic construction of the EMG signals. In the proposed model, an EMG signal variance value is first generated from a probability distribution with a shape determined by a commanded muscle force and signal-dependent noise. Artificial EMG signals are then generated from the associated Gaussian distribution with a zero mean and the generated variance. This facilitates representation of artificial EMG signals with signal-dependent noise superimposed according to the muscle activation levels. The frequency characteristics of the EMG signals are also simulated via a shaping filter with parameters determined by an autoregressive model. An estimation method to determine EMG variance distribution using rectified and smoothed EMG signals, thereby allowing model parameter estimation with a small number of samples, is also incorporated in the proposed model. Moreover, the prediction of variance distribution with strong muscle contraction from EMG signals with low muscle contraction and related artificial EMG generation are also described. The results of experiments conducted, in which the reproduction capability of the proposed model was evaluated through comparison with measured EMG signals in terms of amplitude, frequency content, and EMG distribution demonstrate that the proposed model can reproduce the features of measured EMG signals. Further, utilizing the generated EMG signals as training data for a neural network resulted in the classification of upper limb motion with a higher precision than by learning from only measured EMG signals. This indicates that the proposed model is also applicable to motion classification.

Original languageEnglish
Article numbere0180112
JournalPloS one
Volume12
Issue number6
DOIs
Publication statusPublished - Jun 2017

Fingerprint

electromyography
Electromyography
Muscle
muscle contraction
Muscle Contraction
Gaussian distribution
Parameter estimation
Probability distributions
Chemical activation
Muscles
Neural networks
muscles
Normal Distribution
probability distribution
limbs (animal)
Upper Extremity
neural networks

All Science Journal Classification (ASJC) codes

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

Cite this

An artificial EMG generation model based on signal-dependent noise and related application to motion classification. / Furui, Akira; Hayashi, Hideaki; Nakamura, Go; Chin, Takaaki; Tsuji, Toshio.

In: PloS one, Vol. 12, No. 6, e0180112, 06.2017.

Research output: Contribution to journalArticle

@article{2834fc7770b846c892d98edfee192bc6,
title = "An artificial EMG generation model based on signal-dependent noise and related application to motion classification",
abstract = "This paper proposes an artificial electromyogram (EMG) signal generation model based on signal-dependent noise, which has been ignored in existing methods, by introducing the stochastic construction of the EMG signals. In the proposed model, an EMG signal variance value is first generated from a probability distribution with a shape determined by a commanded muscle force and signal-dependent noise. Artificial EMG signals are then generated from the associated Gaussian distribution with a zero mean and the generated variance. This facilitates representation of artificial EMG signals with signal-dependent noise superimposed according to the muscle activation levels. The frequency characteristics of the EMG signals are also simulated via a shaping filter with parameters determined by an autoregressive model. An estimation method to determine EMG variance distribution using rectified and smoothed EMG signals, thereby allowing model parameter estimation with a small number of samples, is also incorporated in the proposed model. Moreover, the prediction of variance distribution with strong muscle contraction from EMG signals with low muscle contraction and related artificial EMG generation are also described. The results of experiments conducted, in which the reproduction capability of the proposed model was evaluated through comparison with measured EMG signals in terms of amplitude, frequency content, and EMG distribution demonstrate that the proposed model can reproduce the features of measured EMG signals. Further, utilizing the generated EMG signals as training data for a neural network resulted in the classification of upper limb motion with a higher precision than by learning from only measured EMG signals. This indicates that the proposed model is also applicable to motion classification.",
author = "Akira Furui and Hideaki Hayashi and Go Nakamura and Takaaki Chin and Toshio Tsuji",
year = "2017",
month = "6",
doi = "10.1371/journal.pone.0180112",
language = "English",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "6",

}

TY - JOUR

T1 - An artificial EMG generation model based on signal-dependent noise and related application to motion classification

AU - Furui, Akira

AU - Hayashi, Hideaki

AU - Nakamura, Go

AU - Chin, Takaaki

AU - Tsuji, Toshio

PY - 2017/6

Y1 - 2017/6

N2 - This paper proposes an artificial electromyogram (EMG) signal generation model based on signal-dependent noise, which has been ignored in existing methods, by introducing the stochastic construction of the EMG signals. In the proposed model, an EMG signal variance value is first generated from a probability distribution with a shape determined by a commanded muscle force and signal-dependent noise. Artificial EMG signals are then generated from the associated Gaussian distribution with a zero mean and the generated variance. This facilitates representation of artificial EMG signals with signal-dependent noise superimposed according to the muscle activation levels. The frequency characteristics of the EMG signals are also simulated via a shaping filter with parameters determined by an autoregressive model. An estimation method to determine EMG variance distribution using rectified and smoothed EMG signals, thereby allowing model parameter estimation with a small number of samples, is also incorporated in the proposed model. Moreover, the prediction of variance distribution with strong muscle contraction from EMG signals with low muscle contraction and related artificial EMG generation are also described. The results of experiments conducted, in which the reproduction capability of the proposed model was evaluated through comparison with measured EMG signals in terms of amplitude, frequency content, and EMG distribution demonstrate that the proposed model can reproduce the features of measured EMG signals. Further, utilizing the generated EMG signals as training data for a neural network resulted in the classification of upper limb motion with a higher precision than by learning from only measured EMG signals. This indicates that the proposed model is also applicable to motion classification.

AB - This paper proposes an artificial electromyogram (EMG) signal generation model based on signal-dependent noise, which has been ignored in existing methods, by introducing the stochastic construction of the EMG signals. In the proposed model, an EMG signal variance value is first generated from a probability distribution with a shape determined by a commanded muscle force and signal-dependent noise. Artificial EMG signals are then generated from the associated Gaussian distribution with a zero mean and the generated variance. This facilitates representation of artificial EMG signals with signal-dependent noise superimposed according to the muscle activation levels. The frequency characteristics of the EMG signals are also simulated via a shaping filter with parameters determined by an autoregressive model. An estimation method to determine EMG variance distribution using rectified and smoothed EMG signals, thereby allowing model parameter estimation with a small number of samples, is also incorporated in the proposed model. Moreover, the prediction of variance distribution with strong muscle contraction from EMG signals with low muscle contraction and related artificial EMG generation are also described. The results of experiments conducted, in which the reproduction capability of the proposed model was evaluated through comparison with measured EMG signals in terms of amplitude, frequency content, and EMG distribution demonstrate that the proposed model can reproduce the features of measured EMG signals. Further, utilizing the generated EMG signals as training data for a neural network resulted in the classification of upper limb motion with a higher precision than by learning from only measured EMG signals. This indicates that the proposed model is also applicable to motion classification.

UR - http://www.scopus.com/inward/record.url?scp=85021228572&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021228572&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0180112

DO - 10.1371/journal.pone.0180112

M3 - Article

C2 - 28640883

AN - SCOPUS:85021228572

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 6

M1 - e0180112

ER -