Anomaly Detection of Electromyographic Signals

Ahsan Ijaz, Jongeun Choi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we provide a robust framework to detect anomalous electromyographic (EMG) signals and identify contamination types. As a first step for feature selection, optimally selected Lawton wavelets transform is applied. Robust principal component analysis (rPCA) is then performed on these wavelet coefficients to obtain features in a lower dimension. The rPCA based features are used for constructing a self-organizing map (SOM). Finally, hierarchical clustering is applied on the SOM that separates anomalous signals residing in the smaller clusters and breaks them into logical units for contamination identification. The proposed methodology is tested using synthetic and real world EMG signals. The synthetic EMG signals are generated using a heteroscedastic process mimicking desired experimental setups. A sub-part of these synthetic signals is introduced with anomalies. These results are followed with real EMG signals introduced with synthetic anomalies. Finally, a heterogeneous real world data set is used with known quality issues under an unsupervised setting. The framework provides recall of 90% (± 3.3) and precision of 99%(±0.4).

Original languageEnglish
Pages (from-to)770-779
Number of pages10
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume26
Issue number4
DOIs
Publication statusPublished - 2018 Apr 1

Fingerprint

Self organizing maps
Principal Component Analysis
Principal component analysis
Contamination
Wavelet Analysis
Wavelet transforms
Cluster Analysis
Feature extraction
Datasets

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)
  • Biomedical Engineering
  • Computer Science Applications

Cite this

@article{e2e26478cd6e439ab9bf914da1007da6,
title = "Anomaly Detection of Electromyographic Signals",
abstract = "In this paper, we provide a robust framework to detect anomalous electromyographic (EMG) signals and identify contamination types. As a first step for feature selection, optimally selected Lawton wavelets transform is applied. Robust principal component analysis (rPCA) is then performed on these wavelet coefficients to obtain features in a lower dimension. The rPCA based features are used for constructing a self-organizing map (SOM). Finally, hierarchical clustering is applied on the SOM that separates anomalous signals residing in the smaller clusters and breaks them into logical units for contamination identification. The proposed methodology is tested using synthetic and real world EMG signals. The synthetic EMG signals are generated using a heteroscedastic process mimicking desired experimental setups. A sub-part of these synthetic signals is introduced with anomalies. These results are followed with real EMG signals introduced with synthetic anomalies. Finally, a heterogeneous real world data set is used with known quality issues under an unsupervised setting. The framework provides recall of 90{\%} (± 3.3) and precision of 99{\%}(±0.4).",
author = "Ahsan Ijaz and Jongeun Choi",
year = "2018",
month = "4",
day = "1",
doi = "10.1109/TNSRE.2018.2813421",
language = "English",
volume = "26",
pages = "770--779",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

Anomaly Detection of Electromyographic Signals. / Ijaz, Ahsan; Choi, Jongeun.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 26, No. 4, 01.04.2018, p. 770-779.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Anomaly Detection of Electromyographic Signals

AU - Ijaz, Ahsan

AU - Choi, Jongeun

PY - 2018/4/1

Y1 - 2018/4/1

N2 - In this paper, we provide a robust framework to detect anomalous electromyographic (EMG) signals and identify contamination types. As a first step for feature selection, optimally selected Lawton wavelets transform is applied. Robust principal component analysis (rPCA) is then performed on these wavelet coefficients to obtain features in a lower dimension. The rPCA based features are used for constructing a self-organizing map (SOM). Finally, hierarchical clustering is applied on the SOM that separates anomalous signals residing in the smaller clusters and breaks them into logical units for contamination identification. The proposed methodology is tested using synthetic and real world EMG signals. The synthetic EMG signals are generated using a heteroscedastic process mimicking desired experimental setups. A sub-part of these synthetic signals is introduced with anomalies. These results are followed with real EMG signals introduced with synthetic anomalies. Finally, a heterogeneous real world data set is used with known quality issues under an unsupervised setting. The framework provides recall of 90% (± 3.3) and precision of 99%(±0.4).

AB - In this paper, we provide a robust framework to detect anomalous electromyographic (EMG) signals and identify contamination types. As a first step for feature selection, optimally selected Lawton wavelets transform is applied. Robust principal component analysis (rPCA) is then performed on these wavelet coefficients to obtain features in a lower dimension. The rPCA based features are used for constructing a self-organizing map (SOM). Finally, hierarchical clustering is applied on the SOM that separates anomalous signals residing in the smaller clusters and breaks them into logical units for contamination identification. The proposed methodology is tested using synthetic and real world EMG signals. The synthetic EMG signals are generated using a heteroscedastic process mimicking desired experimental setups. A sub-part of these synthetic signals is introduced with anomalies. These results are followed with real EMG signals introduced with synthetic anomalies. Finally, a heterogeneous real world data set is used with known quality issues under an unsupervised setting. The framework provides recall of 90% (± 3.3) and precision of 99%(±0.4).

UR - http://www.scopus.com/inward/record.url?scp=85043379101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043379101&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2018.2813421

DO - 10.1109/TNSRE.2018.2813421

M3 - Article

C2 - 29641381

AN - SCOPUS:85043379101

VL - 26

SP - 770

EP - 779

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 4

ER -