Neural Networks for Atrial Late Potentials Features Detection
Main Article Content
Abstract
The development of information technologies enables to improve tools and diagnostic methods of the cardiovascular system. The new method of electrocardiography is the method of high-resolution electrocardiography ( HR ECG), which allows to detect late potentials (LP) that are low-amplitude components of electrocardiosignal and are invisible on the standard ECG.
In this paper a comprehensive method of processing HR ECG for the classification of electrocardiograms for the presence of atrial late potentials, which are markers of atrial arrhythmias, was proposed. The method is based on the combination of a neural networks algorithm and the classical methods of analysis of cardiac signals: in time domain, spectral and wavelet analysis.
Also, the methods for diagnostic features formation that based on the classical methods of analysis ECG for the training samples construction for neural networks were considered.
The estimation and analysis of the classification of ECG results with presence and absence of abnormalities were made.
Reference 9, figures 8.
Article Details
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Abakumov V.G., Rybin O.I., Svatosh J. (2001), “Biomedical signals. Genesis, treatment, monitoring”. Nora-print. P.526. (Rus)
Akhmed N., Rao K.R., Fomenko N.B. (1980), “Orthogonal transformation of digital signals pro-cessing”. Moskva, Svyaz. P. 248. (Rus)
Bokeriya A.L., Golukhova E.Z., Ivanickyi A.V. (2002), “High resolution electrocardiography / Function-al diagnostics in cardiology”. Vol.1, Moskva, NCSSH Bakuleva RAMN. P. 427. (Rus)
Ivanov G.G., Grachev S.V., Syrkin A.L. (2003), “High resolution electrocardiography”. Moskva, Triada-X. P. 304. (Rus)
Ivanov G.G. (1999), “HR ECG”. http:// www.ecg.ru/books/
Ivanushkina N.G., Fesechko V.O. (2007), “Technologies in high resolution electrocardiography”. Kyiv, NTUU “KPI”. P. 116. (Rus)
Ivanko K.O., Ivanushkina N.G. (2010), “A comprehensive method for atrial late potentials detection”. Naukovi visti, Vol.6. pp. 11-18. (Rus)
Rezishvili A.S., Bokeriya L.A., Golykhova E.Z., Ivanickyi A.V. (2002), “Classification and mechanisms of arrhythmias / Functional diagnostics in cardiology”. Moskva, NCSSH Bakuleva RAMN, Vol. 1. P. 427. (Rus)
Tu J.T., Gonsales R.K. (1978), “Principles of Pattern Recognition”. Moskva, Mir. P. 411. (Rus)