Combined method for detection of atrial late potentials

Author

Matveyeva, N.A. ; Ivanushkina, N.G. ; Ivanko, K.O.

Author_Institution

Phys. & Biomed. Electron., Nat. Tech. Univ. of Ukraine “Kyiv Polytech. Inst.”, Kiev, Ukraine

fYear

2013

fDate

16-19 April 2013

Firstpage

285

Lastpage

289

Abstract

The work is devoted to improvement of methods for noninvasive identification of low-amplitude components of electrocardiogram (ECG) - atrial late potentials (ALP) which are markers of potentially dangerous heart rhythm disorders. A combined method for ALP detection based on wavelet analysis, decomposition in the basis of eigenvectors and classification by neural network is proposed. As the result of the numerical experiment the dimension of ALP feature vector was minimized that made it possible to distinguish between 2 classes "norm - no ALP" and "pathology - ALP are present" with minimum error classification.

Keywords

bioelectric potentials; eigenvalues and eigenfunctions; electrocardiography; medical disorders; medical signal detection; medical signal processing; neural nets; numerical analysis; signal classification; wavelet transforms; ALP detection; ALP feature vector; ECG; atrial late potential detection; decomposition; eigenvector basis; electrocardiogram; heart rhythm disorders; low-amplitude components; minimum error classification; neural network; noninvasive identification; numerical experiment; wavelet analysis; wavelet decomposition; Biological neural networks; Eigenvalues and eigenfunctions; Electrocardiography; Noise; Training; Wavelet analysis; atrial late potentials; eigenvectors basis; high-resolution electrocardiography; markers of atrial tachyarrhythmia; neural network; wavelet analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics and Nanotechnology (ELNANO), 2013 IEEE XXXIII International Scientific Conference

Conference_Location

Kiev

Print_ISBN

978-1-4673-4669-6

Type

conf

DOI

10.1109/ELNANO.2013.6552080

Filename

6552080