An algorithm for EMG noise detection in large ECG data

P. Raphisak, S. C. Schuckers, Amy Curry

Research output: Contribution to journalConference article

7 Citations (Scopus)

Abstract

Large collections of electrocardiogram recordings (ECG) are valuable for researchers. However, some sections of the recorded ECG may be corrupted by electromyogram (EMG) noise from muscle. Therefore, EMG noise needs to be detected and filtered before performing data processing. In this study, an automated algorithm for detecting EMG noise in large ECG data is presented. The algorithm extracts EMG artifact from the ECG by using a morphological filter. EMG is identified by setting a threshold for the moving variance of extracted EMG. The algorithm achieved 100% detection rate on the training data. The algorithm was tested on 150 test signals from three sets of test signals (50 signals in each set). Set 1 was created by adding EMG noise to EMG-free ECG signals, set 2 was manually selected ECG sections which contain EMG noise, and set 3 contained randomly selected ECG signals. Sensitivity was 100%, 94%, and 100% on sets 1, 2, and 3, respectively. All sets had 100% specificity. The algorithm has computational complexity of O(N).

Original languageEnglish (US)
Pages (from-to)369-372
Number of pages4
JournalComputers in Cardiology
Volume31
StatePublished - Dec 1 2004
Externally publishedYes
EventComputers in Cardiology 2004 - Chicago, IL, United States
Duration: Sep 19 2004Sep 22 2004

Fingerprint

Data recording
Electromyography
Electrocardiography
Noise
Muscle
Computational complexity
Artifacts
Research Personnel
Muscles

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine
  • Software

Cite this

An algorithm for EMG noise detection in large ECG data. / Raphisak, P.; Schuckers, S. C.; Curry, Amy.

In: Computers in Cardiology, Vol. 31, 01.12.2004, p. 369-372.

Research output: Contribution to journalConference article

Raphisak, P, Schuckers, SC & Curry, A 2004, 'An algorithm for EMG noise detection in large ECG data', Computers in Cardiology, vol. 31, pp. 369-372.
Raphisak, P. ; Schuckers, S. C. ; Curry, Amy. / An algorithm for EMG noise detection in large ECG data. In: Computers in Cardiology. 2004 ; Vol. 31. pp. 369-372.
@article{9c395cd4460c496c9672026d55fd6771,
title = "An algorithm for EMG noise detection in large ECG data",
abstract = "Large collections of electrocardiogram recordings (ECG) are valuable for researchers. However, some sections of the recorded ECG may be corrupted by electromyogram (EMG) noise from muscle. Therefore, EMG noise needs to be detected and filtered before performing data processing. In this study, an automated algorithm for detecting EMG noise in large ECG data is presented. The algorithm extracts EMG artifact from the ECG by using a morphological filter. EMG is identified by setting a threshold for the moving variance of extracted EMG. The algorithm achieved 100{\%} detection rate on the training data. The algorithm was tested on 150 test signals from three sets of test signals (50 signals in each set). Set 1 was created by adding EMG noise to EMG-free ECG signals, set 2 was manually selected ECG sections which contain EMG noise, and set 3 contained randomly selected ECG signals. Sensitivity was 100{\%}, 94{\%}, and 100{\%} on sets 1, 2, and 3, respectively. All sets had 100{\%} specificity. The algorithm has computational complexity of O(N).",
author = "P. Raphisak and Schuckers, {S. C.} and Amy Curry",
year = "2004",
month = "12",
day = "1",
language = "English (US)",
volume = "31",
pages = "369--372",
journal = "Computing in Cardiology",
issn = "2325-8861",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - An algorithm for EMG noise detection in large ECG data

AU - Raphisak, P.

AU - Schuckers, S. C.

AU - Curry, Amy

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Large collections of electrocardiogram recordings (ECG) are valuable for researchers. However, some sections of the recorded ECG may be corrupted by electromyogram (EMG) noise from muscle. Therefore, EMG noise needs to be detected and filtered before performing data processing. In this study, an automated algorithm for detecting EMG noise in large ECG data is presented. The algorithm extracts EMG artifact from the ECG by using a morphological filter. EMG is identified by setting a threshold for the moving variance of extracted EMG. The algorithm achieved 100% detection rate on the training data. The algorithm was tested on 150 test signals from three sets of test signals (50 signals in each set). Set 1 was created by adding EMG noise to EMG-free ECG signals, set 2 was manually selected ECG sections which contain EMG noise, and set 3 contained randomly selected ECG signals. Sensitivity was 100%, 94%, and 100% on sets 1, 2, and 3, respectively. All sets had 100% specificity. The algorithm has computational complexity of O(N).

AB - Large collections of electrocardiogram recordings (ECG) are valuable for researchers. However, some sections of the recorded ECG may be corrupted by electromyogram (EMG) noise from muscle. Therefore, EMG noise needs to be detected and filtered before performing data processing. In this study, an automated algorithm for detecting EMG noise in large ECG data is presented. The algorithm extracts EMG artifact from the ECG by using a morphological filter. EMG is identified by setting a threshold for the moving variance of extracted EMG. The algorithm achieved 100% detection rate on the training data. The algorithm was tested on 150 test signals from three sets of test signals (50 signals in each set). Set 1 was created by adding EMG noise to EMG-free ECG signals, set 2 was manually selected ECG sections which contain EMG noise, and set 3 contained randomly selected ECG signals. Sensitivity was 100%, 94%, and 100% on sets 1, 2, and 3, respectively. All sets had 100% specificity. The algorithm has computational complexity of O(N).

UR - http://www.scopus.com/inward/record.url?scp=28144438569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28144438569&partnerID=8YFLogxK

M3 - Conference article

VL - 31

SP - 369

EP - 372

JO - Computing in Cardiology

JF - Computing in Cardiology

SN - 2325-8861

ER -