Geometric detection algorithm design for ECG data analysis using wavelet

Seo Joon Lee, Yun Ho Roh, Yong Kwon Kim, Tae Ro Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The need for clear ECG signals is increasing to reduce the probability of misdiagnosis regarding heart diseases. An algorithm was designed to diagnose patients with heart diseases using ECG signal analysis so that it can help physicians in the decision-making process. Before analyzing the ECG signal, noise of the low and high frequency components was removed through preprocessing. After preprocessing, pattern analysis detected important features on which diagnosis will be given. Then, the analysis was applied on the pure ECG signal to detect the patient's heart diseases. All feature points were extracted by using the proposed algorithm, called 'Geometric Detection (GD)'. Results showed that performance was superior to others in standard error of the sample mean and variance. Data from CSE (Common Standards for Electrocardiography) database were used to test each algorithm except for GD, because patients' ECG data was used to test the GD algorithm. Detection rate of the GD algorithm (se(%)) was 99.1% and we confirmed that the proposed algorithm is superior to the other algorithm in terms of stability and standard error of the sample mean. The result of the performance evaluation showed that the proposed algorithm produced higher accuracy and stability than the other algorithms.

Original languageEnglish
Pages (from-to)11-23
Number of pages13
JournalInternational Journal of Bio-Science and Bio-Technology
Volume5
Issue number4
Publication statusPublished - 2013 Sep 10

Fingerprint

Electrocardiography
Heart Diseases
Signal analysis
Diagnostic Errors
Noise
Decision Making
Decision making
Databases
Physicians

Keywords

  • ECG characteristic
  • Geometric detection algorithm
  • Wavelet

ASJC Scopus subject areas

  • Biomedical Engineering
  • Biotechnology
  • Bioengineering
  • Artificial Intelligence

Cite this

Geometric detection algorithm design for ECG data analysis using wavelet. / Lee, Seo Joon; Roh, Yun Ho; Kim, Yong Kwon; Lee, Tae Ro.

In: International Journal of Bio-Science and Bio-Technology, Vol. 5, No. 4, 10.09.2013, p. 11-23.

Research output: Contribution to journalArticle

@article{3f481906e57c4bf4bb0e9cff95b313a6,
title = "Geometric detection algorithm design for ECG data analysis using wavelet",
abstract = "The need for clear ECG signals is increasing to reduce the probability of misdiagnosis regarding heart diseases. An algorithm was designed to diagnose patients with heart diseases using ECG signal analysis so that it can help physicians in the decision-making process. Before analyzing the ECG signal, noise of the low and high frequency components was removed through preprocessing. After preprocessing, pattern analysis detected important features on which diagnosis will be given. Then, the analysis was applied on the pure ECG signal to detect the patient's heart diseases. All feature points were extracted by using the proposed algorithm, called 'Geometric Detection (GD)'. Results showed that performance was superior to others in standard error of the sample mean and variance. Data from CSE (Common Standards for Electrocardiography) database were used to test each algorithm except for GD, because patients' ECG data was used to test the GD algorithm. Detection rate of the GD algorithm (se({\%})) was 99.1{\%} and we confirmed that the proposed algorithm is superior to the other algorithm in terms of stability and standard error of the sample mean. The result of the performance evaluation showed that the proposed algorithm produced higher accuracy and stability than the other algorithms.",
keywords = "ECG characteristic, Geometric detection algorithm, Wavelet",
author = "Lee, {Seo Joon} and Roh, {Yun Ho} and Kim, {Yong Kwon} and Lee, {Tae Ro}",
year = "2013",
month = "9",
day = "10",
language = "English",
volume = "5",
pages = "11--23",
journal = "International Journal of Bio-Science and Bio-Technology",
issn = "2233-7849",
publisher = "Science and Engineering Research Support Society",
number = "4",

}

TY - JOUR

T1 - Geometric detection algorithm design for ECG data analysis using wavelet

AU - Lee, Seo Joon

AU - Roh, Yun Ho

AU - Kim, Yong Kwon

AU - Lee, Tae Ro

PY - 2013/9/10

Y1 - 2013/9/10

N2 - The need for clear ECG signals is increasing to reduce the probability of misdiagnosis regarding heart diseases. An algorithm was designed to diagnose patients with heart diseases using ECG signal analysis so that it can help physicians in the decision-making process. Before analyzing the ECG signal, noise of the low and high frequency components was removed through preprocessing. After preprocessing, pattern analysis detected important features on which diagnosis will be given. Then, the analysis was applied on the pure ECG signal to detect the patient's heart diseases. All feature points were extracted by using the proposed algorithm, called 'Geometric Detection (GD)'. Results showed that performance was superior to others in standard error of the sample mean and variance. Data from CSE (Common Standards for Electrocardiography) database were used to test each algorithm except for GD, because patients' ECG data was used to test the GD algorithm. Detection rate of the GD algorithm (se(%)) was 99.1% and we confirmed that the proposed algorithm is superior to the other algorithm in terms of stability and standard error of the sample mean. The result of the performance evaluation showed that the proposed algorithm produced higher accuracy and stability than the other algorithms.

AB - The need for clear ECG signals is increasing to reduce the probability of misdiagnosis regarding heart diseases. An algorithm was designed to diagnose patients with heart diseases using ECG signal analysis so that it can help physicians in the decision-making process. Before analyzing the ECG signal, noise of the low and high frequency components was removed through preprocessing. After preprocessing, pattern analysis detected important features on which diagnosis will be given. Then, the analysis was applied on the pure ECG signal to detect the patient's heart diseases. All feature points were extracted by using the proposed algorithm, called 'Geometric Detection (GD)'. Results showed that performance was superior to others in standard error of the sample mean and variance. Data from CSE (Common Standards for Electrocardiography) database were used to test each algorithm except for GD, because patients' ECG data was used to test the GD algorithm. Detection rate of the GD algorithm (se(%)) was 99.1% and we confirmed that the proposed algorithm is superior to the other algorithm in terms of stability and standard error of the sample mean. The result of the performance evaluation showed that the proposed algorithm produced higher accuracy and stability than the other algorithms.

KW - ECG characteristic

KW - Geometric detection algorithm

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=84883482683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883482683&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 11

EP - 23

JO - International Journal of Bio-Science and Bio-Technology

JF - International Journal of Bio-Science and Bio-Technology

SN - 2233-7849

IS - 4

ER -