A multi-stage neural network classifier for ECG events

被引：18

作者：

Hosseini, HG ^{[1
]}

Reynolds, KJ ^{[1
]}

Powers, D ^{[1
]}

机构：

[1] Univ Auckland Technol, Dept Electrotechnol, Auckland, New Zealand

来源：

PROCEEDINGS OF THE 23RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-4: BUILDING NEW BRIDGES AT THE FRONTIERS OF ENGINEERING AND MEDICINE | 2001年 / 23卷

关键词：

ECG event classifier; artificial neural network (ANN); ECG signal diagnosis;

D O I：

10.1109/IEMBS.2001.1020536

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

In this paper, a multi-stage network including two multilayer perceptron (MLP) and one self organizing map (SOM) networks is presented. The input of the network is a combination of independent features and the compressed ElectroCardioGram (ECG) data. The proposed network as a form of data fusion, performs better than using the raw data or individual features. We classified six common ECG waveforms using ten ECG records of the MIT/BIH arrhythmia database. An average recognition rate of 0.883 was achieved within a short training and testing time.

引用

页码：1672 / 1675

页数：4

共 16 条

[1]

AFONSO VX, 1995, IEEE ENG MED BIO MAR, P152

[2]

Badr A., 1993, THESIS RIJKSUNIVERSI

[3]

Bishop C. M., 1995, NEURAL NETWORKS PATT

[4]

Celler BG, 1998, P ANN INT IEEE EMBS, V20, P1337, DOI 10.1109/IEMBS.1998.747126

[5]

CHAZAL P, 1998, P 20 ANN INT C IEEE, V20, P1422

[6]

HAN S, 1993, THESIS FLORIDA I TEC

[7]

HOSSEINI HG, 1998, AUSTR PHYSICAL ENG S, V21, P186

[8] A patient-adaptable ECG beat classifier using a mixture of experts approach [J].

Hu, Yu Hen ;

Palreddy, Surekha ;

Tompkins, Willis J. .

1997, IEEE, Piscataway, NJ, United States (44)

[9]

Looney C. G., 1997, PATTERN RECOGNITION

[10] REVIEW OF NEURAL NETWORK APPLICATIONS IN MEDICAL IMAGING AND SIGNAL-PROCESSING [J].

MILLER, AS ;

BLOTT, BH ;

HAMES, TK .

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 1992, 30 (05) :449-464

← 1 2 →