Comparison of discrete wavelet and Fourier transforms for ECG beat classification

Z. Dokur; T. Ölmez; E. Yazgan

doi:10.1049/el:19991095

Comparison of discrete wavelet and Fourier transforms for ECG beat classification

Z. Dokur^*
, T. Ölmez
, E. Yazgan

^*Corresponding author for this work

Department of Electronics and Communication Engineering

Istanbul Technical University

Research output: Contribution to journal › Article › peer-review

69 Citations (Scopus)

Abstract

Two feature extraction methods, Fourier and wavelet analyses for ECG beat classification, are comparatively investigated. ECG features are searched by dynamic programming according to the divergence values. 10 types of ECG beat from an MIT-BIH database are classified with a success of 97% using a restricted Coulomb energy neural network trained by genetic algorithms.

Original language	English
Pages (from-to)	1502-1504
Number of pages	3
Journal	Electronics Letters
Volume	35
Issue number	18
DOIs	https://doi.org/10.1049/el:19991095
Publication status	Published - 2 Sept 1999

Access to Document

10.1049/el:19991095

Cite this

@article{62f138a73bac4cbdb2f434075a3c4333,

title = "Comparison of discrete wavelet and Fourier transforms for ECG beat classification",

abstract = "Two feature extraction methods, Fourier and wavelet analyses for ECG beat classification, are comparatively investigated. ECG features are searched by dynamic programming according to the divergence values. 10 types of ECG beat from an MIT-BIH database are classified with a success of 97\% using a restricted Coulomb energy neural network trained by genetic algorithms.",

author = "Z. Dokur and T. {\"O}lmez and E. Yazgan",

year = "1999",

month = sep,

day = "2",

doi = "10.1049/el:19991095",

language = "English",

volume = "35",

pages = "1502--1504",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley \& Sons Inc.",

number = "18",

}

TY - JOUR

T1 - Comparison of discrete wavelet and Fourier transforms for ECG beat classification

AU - Dokur, Z.

AU - Ölmez, T.

AU - Yazgan, E.

PY - 1999/9/2

Y1 - 1999/9/2

N2 - Two feature extraction methods, Fourier and wavelet analyses for ECG beat classification, are comparatively investigated. ECG features are searched by dynamic programming according to the divergence values. 10 types of ECG beat from an MIT-BIH database are classified with a success of 97% using a restricted Coulomb energy neural network trained by genetic algorithms.

AB - Two feature extraction methods, Fourier and wavelet analyses for ECG beat classification, are comparatively investigated. ECG features are searched by dynamic programming according to the divergence values. 10 types of ECG beat from an MIT-BIH database are classified with a success of 97% using a restricted Coulomb energy neural network trained by genetic algorithms.

UR - https://www.scopus.com/pages/publications/0033359340

U2 - 10.1049/el:19991095

DO - 10.1049/el:19991095

M3 - Article

AN - SCOPUS:0033359340

SN - 0013-5194

VL - 35

SP - 1502

EP - 1504

JO - Electronics Letters

JF - Electronics Letters

IS - 18

ER -

Comparison of discrete wavelet and Fourier transforms for ECG beat classification

Abstract

Access to Document

Other files and links

Fingerprint

Cite this