Neural and traditional techniques in diagnostic ECG classification

Author

Silipo, Rosaria ; Bortolan, Giovanni

Author_Institution

Dept. of Syst. & Inf., Florence Univ., Italy

Volume

1

fYear

1997

fDate

21-24 Apr 1997

Firstpage

123

Abstract

Neural and traditional techniques have been compared for the particular task of automatic ECG analysis. A large validated ECG database has been used. Statistical methods, neural architectures with supervised and unsupervised learning, and a neuro fuzzy architecture have been considered. The results from the connectionist approach are always at least comparable with those coming from more traditional classification methods. But the best performances have been obtained by the combination of the connectionist with the fuzzy approach

Keywords

electrocardiography; fuzzy neural nets; learning (artificial intelligence); medical diagnostic computing; medical signal processing; neural net architecture; pattern classification; automatic ECG analysis; connectionist approach; diagnostic ECG classification; fuzzy approach; large validated ECG database; neural architectures; neural techniques; neuro fuzzy architecture; statistical methods; supervised learning; traditional techniques; unsupervised learning; Clustering methods; Databases; Diagnostic expert systems; Electrocardiography; Failure analysis; Medical diagnostic imaging; Pathology; Signal analysis; Testing; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.599566

Filename

599566