An automatic neural-network based SVT/VT classification system

Author

Thomson, D.C. ; Soraghan, J.J. ; Durrani, T.S.

Author_Institution

Signal Process. Div., Strathclyde Univ., Glasgow, UK

fYear

1993

fDate

5-8 Sep 1993

Firstpage

333

Lastpage

336

Abstract

Describes a novel automatic ECG rhythm analysis system for the problem of classifying between normal sinus rhythm (NSR), supraventricular tachycardia (SVT) and ventricular tachycardia (VT). The system comprises two stages-a preprocessing stage and a neural network based classification stage. The preprocessing stage performs feature vector extraction from multi-leaded ECG sources. Key temporal (morphological), spatial (inter-lead) and spectral (frequency) features are used to form the feature vectors. The neural network classifier comprises a multi-layer perceptron trained using the backpropagation algorithm. By fusing features from the spectral and temporal domains, 100% classification is again possible

Keywords

electrocardiography; medical signal processing; automatic neural-network based SVT/VT classification system; backpropagation algorithm; feature vectors; multilayer perceptron; multileaded ECG sources; neural network based classification stage; normal sinus rhythm; preprocessing stage; spatial features; spectral features; supraventricular tachycardia; temporal features; ventricular tachycardia; Data mining; Discrete Fourier transforms; Electrocardiography; Frequency domain analysis; Frequency measurement; Mathematical model; Multi-layer neural network; Neural networks; Rhythm; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers in Cardiology 1993, Proceedings.

Conference_Location

London

Print_ISBN

0-8186-5470-8

Type

conf

DOI

10.1109/CIC.1993.378436

Filename

378436