A multiple-classifier architecture for ECG beat classification

Author

Palreddy, Surekha ; Hu, Yu Hen ; Mani, Vijay ; Tompkins, Willis J.

Author_Institution

Dept. of Electr. & Comput. Eng., Wisconsin Univ., Madison, WI, USA

fYear

1997

fDate

24-26 Sep 1997

Firstpage

172

Lastpage

181

Abstract

We investigate the use of the modular architecture of multiple clustering based pattern classifiers for ECG beat classification using the MIT/BIH arrhythmia database. The feature space is divided into several regions and individual classifiers are developed for each region separately. Then the outputs of these classifiers are combined using two competing combination rules: a winner decides all method and a distance-based combination method. Experiment results indicated that multiple classifier approach yields better sensitivity and classification rate

Keywords

divide and conquer methods; electrocardiography; learning (artificial intelligence); medical signal processing; pattern classification; self-organising feature maps; ECG beat classification; MIT/BIH arrhythmia database; distance-based combination method; multiple-classifier architecture; winner decides all method; Computer architecture; Electrocardiography; Heart beat; Heart rate variability; Morphology; Pattern classification; Self organizing feature maps; Shape; Spatial databases; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop

Conference_Location

Amelia Island, FL

ISSN

1089-3555

Print_ISBN

0-7803-4256-9

Type

conf

DOI

10.1109/NNSP.1997.622396

Filename

622396