Comparison of discrete wavelet and Fourier transforms for ECG beat classification

被引：48

作者：

Dokur, Z ^{[1
]}

Ölmez, T ^{[1
]}

Yazgan, E ^{[1
]}

机构：

[1] Istanbul Tech Univ, Dept Elect & Commun Engn, TR-80626 Istanbul, Turkey

来源：

ELECTRONICS LETTERS | 1999年 / 35卷 / 18期

关键词：

D O I：

10.1049/el:19991095

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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 mural network trained by genetic algorithms.

引用

页码：1502 / 1504

页数：3

共 4 条

[1] ECG beat detection using filter banks
Afonso, VX
Tompkins, WJ
Nguyen, TQ
Luo, S
[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1999, 46 (02) : 192 - 202
[2] Classification of ECG waveforms by using RCE neural network and genetic algorithms
Olmez, T
[J]. ELECTRONICS LETTERS, 1997, 33 (18) : 1561 - 1562
[3] COMPARING WAVELET TRANSFORMS FOR RECOGNIZING CARDIAC PATTERNS
SENHADJI, L
CARRAULT, G
BELLANGER, JJ
PASSARIELLO, G
[J]. IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 1995, 14 (02): : 167 - 173
[4] YU X, 1996, 18 ANN INT C IEEE EM

← 1 →