A Scale Mixture-Based Stochastic Model of Surface EMG Signals with Variable Variances

Akira Furui, Hideaki Hayashi, Toshio Tsuji

Research output: Contribution to journalArticle

Abstract

Surface electromyogram (EMG) signals have typically been assumed to follow a Gaussian distribution. However, the presence of non-Gaussian signals associated with muscle activity has been reported in recent studies, and there is no general model of the distribution of EMG signals that can explain both non-Gaussian and Gaussian distributions within a unified scheme. Methods: In this paper, we describe the formulation of a non-Gaussian EMG model based on a scale mixture distribution. In the model, an EMG signal at a certain time follows a Gaussian distribution, and its variance is handled as a random variable that follows an inverse gamma distribution. Accordingly, the probability distribution of EMG signals is assumed to be a mixture of Gaussians with the same mean but different variances. The EMG variance distribution is estimated via marginal likelihood maximization. Results: Experiments involving nine participants revealed that the proposed model provides a better fit to recorded EMG signals than conventional EMG models. It was also shown that variance distribution parameters may reflect underlying motor unit activity. Conclusion: This study proposed a scale mixture distribution-based stochastic EMG model capable of representing changes in non-Gaussianity associated with muscle activity. A series of experiments demonstrated the validity of the model and highlighted the relationship between the variance distribution and muscle force. Significance: The proposed model helps to clarify conventional wisdom regarding the probability distribution of surface EMG signals within a unified scheme.

Original languageEnglish
Article number8627996
Pages (from-to)2780-2788
Number of pages9
JournalIEEE Transactions on Biomedical Engineering
Volume66
Issue number10
DOIs
Publication statusPublished - Oct 2019

Fingerprint

Stochastic models
Gaussian distribution
Muscle
Probability distributions
Random variables
Experiments

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

A Scale Mixture-Based Stochastic Model of Surface EMG Signals with Variable Variances. / Furui, Akira; Hayashi, Hideaki; Tsuji, Toshio.

In: IEEE Transactions on Biomedical Engineering, Vol. 66, No. 10, 8627996, 10.2019, p. 2780-2788.

Research output: Contribution to journalArticle

@article{1dcdd174d8b142af91598ec156074bbf,
title = "A Scale Mixture-Based Stochastic Model of Surface EMG Signals with Variable Variances",
abstract = "Surface electromyogram (EMG) signals have typically been assumed to follow a Gaussian distribution. However, the presence of non-Gaussian signals associated with muscle activity has been reported in recent studies, and there is no general model of the distribution of EMG signals that can explain both non-Gaussian and Gaussian distributions within a unified scheme. Methods: In this paper, we describe the formulation of a non-Gaussian EMG model based on a scale mixture distribution. In the model, an EMG signal at a certain time follows a Gaussian distribution, and its variance is handled as a random variable that follows an inverse gamma distribution. Accordingly, the probability distribution of EMG signals is assumed to be a mixture of Gaussians with the same mean but different variances. The EMG variance distribution is estimated via marginal likelihood maximization. Results: Experiments involving nine participants revealed that the proposed model provides a better fit to recorded EMG signals than conventional EMG models. It was also shown that variance distribution parameters may reflect underlying motor unit activity. Conclusion: This study proposed a scale mixture distribution-based stochastic EMG model capable of representing changes in non-Gaussianity associated with muscle activity. A series of experiments demonstrated the validity of the model and highlighted the relationship between the variance distribution and muscle force. Significance: The proposed model helps to clarify conventional wisdom regarding the probability distribution of surface EMG signals within a unified scheme.",
author = "Akira Furui and Hideaki Hayashi and Toshio Tsuji",
year = "2019",
month = "10",
doi = "10.1109/TBME.2019.2895683",
language = "English",
volume = "66",
pages = "2780--2788",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - A Scale Mixture-Based Stochastic Model of Surface EMG Signals with Variable Variances

AU - Furui, Akira

AU - Hayashi, Hideaki

AU - Tsuji, Toshio

PY - 2019/10

Y1 - 2019/10

N2 - Surface electromyogram (EMG) signals have typically been assumed to follow a Gaussian distribution. However, the presence of non-Gaussian signals associated with muscle activity has been reported in recent studies, and there is no general model of the distribution of EMG signals that can explain both non-Gaussian and Gaussian distributions within a unified scheme. Methods: In this paper, we describe the formulation of a non-Gaussian EMG model based on a scale mixture distribution. In the model, an EMG signal at a certain time follows a Gaussian distribution, and its variance is handled as a random variable that follows an inverse gamma distribution. Accordingly, the probability distribution of EMG signals is assumed to be a mixture of Gaussians with the same mean but different variances. The EMG variance distribution is estimated via marginal likelihood maximization. Results: Experiments involving nine participants revealed that the proposed model provides a better fit to recorded EMG signals than conventional EMG models. It was also shown that variance distribution parameters may reflect underlying motor unit activity. Conclusion: This study proposed a scale mixture distribution-based stochastic EMG model capable of representing changes in non-Gaussianity associated with muscle activity. A series of experiments demonstrated the validity of the model and highlighted the relationship between the variance distribution and muscle force. Significance: The proposed model helps to clarify conventional wisdom regarding the probability distribution of surface EMG signals within a unified scheme.

AB - Surface electromyogram (EMG) signals have typically been assumed to follow a Gaussian distribution. However, the presence of non-Gaussian signals associated with muscle activity has been reported in recent studies, and there is no general model of the distribution of EMG signals that can explain both non-Gaussian and Gaussian distributions within a unified scheme. Methods: In this paper, we describe the formulation of a non-Gaussian EMG model based on a scale mixture distribution. In the model, an EMG signal at a certain time follows a Gaussian distribution, and its variance is handled as a random variable that follows an inverse gamma distribution. Accordingly, the probability distribution of EMG signals is assumed to be a mixture of Gaussians with the same mean but different variances. The EMG variance distribution is estimated via marginal likelihood maximization. Results: Experiments involving nine participants revealed that the proposed model provides a better fit to recorded EMG signals than conventional EMG models. It was also shown that variance distribution parameters may reflect underlying motor unit activity. Conclusion: This study proposed a scale mixture distribution-based stochastic EMG model capable of representing changes in non-Gaussianity associated with muscle activity. A series of experiments demonstrated the validity of the model and highlighted the relationship between the variance distribution and muscle force. Significance: The proposed model helps to clarify conventional wisdom regarding the probability distribution of surface EMG signals within a unified scheme.

UR - http://www.scopus.com/inward/record.url?scp=85077383079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077383079&partnerID=8YFLogxK

U2 - 10.1109/TBME.2019.2895683

DO - 10.1109/TBME.2019.2895683

M3 - Article

AN - SCOPUS:85077383079

VL - 66

SP - 2780

EP - 2788

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

M1 - 8627996

ER -