Detection of ventricular Arrhythmias using roots location in AR-modelling

Author

Kafieh, Rahele ; Mehri, Alireza ; Amirfattahi, Rassoul

Author_Institution

Isfahahan Univ. of Med., Isfahahan

fYear

2007

fDate

10-13 Dec. 2007

Firstpage

1

Lastpage

4

Abstract

This paper addresses the problem of automatic discrimination of rhythms in ECG signals. In performing the discrimination, fourth-order AR parameters of successive segments are estimated and the related roots are computed and used as inputs to the learning vector quantization (LVQ) classification algorithm. In discriminating normal (NSR) rhythm from arrhythmias, 98% of normal data and 88% of data with arrhythmia are classified correctly. Also in discriminating VF from VT, 72% of data with VF and 86% of data with VT are determined properly.

Keywords

autoregressive processes; electrocardiography; learning (artificial intelligence); medical diagnostic computing; medical signal processing; patient diagnosis; pattern classification; vector quantisation; ECG signals; LVQ classification algorithm; autoregressive modelling; discriminating normal rhythm; fourth-order AR parameters; learning vector quantization; roots location; ventricular arrhythmias detection; Biomedical engineering; Electrocardiography; Fast Fourier transforms; Feature extraction; Fibrillation; Frequency estimation; Heart; Reliability engineering; Rhythm; Time domain analysis; Autoregressive modeling; Electrocardiogram (ECG); LVQ networks; ventricular fibrillation (VF); ventricular tachycardia (VT);

fLanguage

English

Publisher

ieee

Conference_Titel

Information, Communications & Signal Processing, 2007 6th International Conference on

Conference_Location

Singapore

Print_ISBN

978-1-4244-0982-2

Electronic_ISBN

978-1-4244-0983-9

Type

conf

DOI

10.1109/ICICS.2007.4449541

Filename

4449541