Electrocardiogram compression using artificial neural networks

W.A. Sandham, D.C. Thomson, D.J. Hamilton

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With increasing use of the electrocardiogram (EGG) as a diagnostic tool in cardiology, there exists a requirement for effective ECG compression techniques. This paper describes such a technique based on artificial neural networks (ANNs), and gives detailed results of pregrouping techniques used to improve the performance of an autoassociative compression network. The ANN algorithms used for grouping are a simple competitive learning network, fuzzy min-max clustering and fuzzy ART. The advantages of using principal components analysis (PCA) prior to grouping are discussed, and the results of this approach applied to a large real world data set are presented.
Original languageEnglish
Title of host publicationIEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995
PublisherIEEE
Pages18-25
Number of pages8
ISBN (Print)9780780324756
DOIs
Publication statusPublished - 1995
Externally publishedYes

Publication series

NameIEEE Annual Conference Engineering in Medicine and Biology Society
PublisherIEEE
ISSN (Print)1557-170X

Fingerprint

Electrocardiography
Neural networks
Cardiology
Principal component analysis

Cite this

Sandham, W. A., Thomson, D. C., & Hamilton, D. J. (1995). Electrocardiogram compression using artificial neural networks. In IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995 (pp. 18-25). (IEEE Annual Conference Engineering in Medicine and Biology Society ). IEEE. https://doi.org/10.1109/IEMBS.1995.575066
Sandham, W.A. ; Thomson, D.C. ; Hamilton, D.J. / Electrocardiogram compression using artificial neural networks. IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995 . IEEE, 1995. pp. 18-25 (IEEE Annual Conference Engineering in Medicine and Biology Society ).
@inproceedings{c278100a12b64e14a22c3edd6471a43b,
title = "Electrocardiogram compression using artificial neural networks",
abstract = "With increasing use of the electrocardiogram (EGG) as a diagnostic tool in cardiology, there exists a requirement for effective ECG compression techniques. This paper describes such a technique based on artificial neural networks (ANNs), and gives detailed results of pregrouping techniques used to improve the performance of an autoassociative compression network. The ANN algorithms used for grouping are a simple competitive learning network, fuzzy min-max clustering and fuzzy ART. The advantages of using principal components analysis (PCA) prior to grouping are discussed, and the results of this approach applied to a large real world data set are presented.",
author = "W.A. Sandham and D.C. Thomson and D.J. Hamilton",
year = "1995",
doi = "10.1109/IEMBS.1995.575066",
language = "English",
isbn = "9780780324756",
series = "IEEE Annual Conference Engineering in Medicine and Biology Society",
publisher = "IEEE",
pages = "18--25",
booktitle = "IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995",
address = "United States",

}

Sandham, WA, Thomson, DC & Hamilton, DJ 1995, Electrocardiogram compression using artificial neural networks. in IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995 . IEEE Annual Conference Engineering in Medicine and Biology Society , IEEE, pp. 18-25. https://doi.org/10.1109/IEMBS.1995.575066

Electrocardiogram compression using artificial neural networks. / Sandham, W.A.; Thomson, D.C.; Hamilton, D.J.

IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995 . IEEE, 1995. p. 18-25 (IEEE Annual Conference Engineering in Medicine and Biology Society ).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Electrocardiogram compression using artificial neural networks

AU - Sandham, W.A.

AU - Thomson, D.C.

AU - Hamilton, D.J.

PY - 1995

Y1 - 1995

N2 - With increasing use of the electrocardiogram (EGG) as a diagnostic tool in cardiology, there exists a requirement for effective ECG compression techniques. This paper describes such a technique based on artificial neural networks (ANNs), and gives detailed results of pregrouping techniques used to improve the performance of an autoassociative compression network. The ANN algorithms used for grouping are a simple competitive learning network, fuzzy min-max clustering and fuzzy ART. The advantages of using principal components analysis (PCA) prior to grouping are discussed, and the results of this approach applied to a large real world data set are presented.

AB - With increasing use of the electrocardiogram (EGG) as a diagnostic tool in cardiology, there exists a requirement for effective ECG compression techniques. This paper describes such a technique based on artificial neural networks (ANNs), and gives detailed results of pregrouping techniques used to improve the performance of an autoassociative compression network. The ANN algorithms used for grouping are a simple competitive learning network, fuzzy min-max clustering and fuzzy ART. The advantages of using principal components analysis (PCA) prior to grouping are discussed, and the results of this approach applied to a large real world data set are presented.

U2 - 10.1109/IEMBS.1995.575066

DO - 10.1109/IEMBS.1995.575066

M3 - Conference contribution

SN - 9780780324756

T3 - IEEE Annual Conference Engineering in Medicine and Biology Society

SP - 18

EP - 25

BT - IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995

PB - IEEE

ER -

Sandham WA, Thomson DC, Hamilton DJ. Electrocardiogram compression using artificial neural networks. In IEEE 17th Annual Conference Engineering in Medicine and Biology Society, 1995 . IEEE. 1995. p. 18-25. (IEEE Annual Conference Engineering in Medicine and Biology Society ). https://doi.org/10.1109/IEMBS.1995.575066