DocumentCode
1804484
Title
Comparison of artificial neural network based ECG classifiers using different features types
Author
De Sá, J. P Marques ; Gonçalves, A.P. ; Ferreira, F.O. ; Abreu-Lima, C.
Author_Institution
Fac. de Engenharia, Porto Univ., Portugal
fYear
1994
fDate
25-28 Sept. 1994
Firstpage
545
Lastpage
547
Abstract
Artificial neural networks (ANN) have been applied for some years in the field of signal classification with the aim of outperforming the traditional classifiers. The authors address the results of a study that comprehended the design and training of ANNs for ECG classification in four classes. Distinct ANNs having as inputs distinct ECG features types were designed and trained with the aim of attaining a reduced and "best" discriminating features set.<>
Keywords
electrocardiography; medical signal processing; multilayer perceptrons; artificial neural network based ECG classifiers; features types; medical diagnostic technique; neural network design; neural network training; reduced/best discriminating features set; signal classification; Artificial neural networks; Backpropagation algorithms; Data mining; Electrocardiography; Hospitals; Multilayer perceptrons; Myocardium; Pattern classification; Personal communication networks; Software packages;
fLanguage
English
Publisher
ieee
Conference_Titel
Computers in Cardiology 1994
Conference_Location
Bethesda, MD, USA
Print_ISBN
0-8186-6570-X
Type
conf
DOI
10.1109/CIC.1994.470134
Filename
470134
Link To Document