Article

Article title ARTIFICIAL NEURAL NETWORK BASED ON RADIAL BASIS FUNCTIONS FOR CLASSIFICATION OF CARDIOCYCLES OF ELECTROCARDIOSIGNALS
Authors Zaw Zaw Tun, S.A. Filist
Section SECTION I. HARDWARE AND SOFTWARE OF FUNCTIONAL DIAGNOSTICS AND THERAPY
Month, Year 08, 2010 @en
Index UDC 615.47
DOI
Abstract The approach for classification of cardiocycles of electrocardiosignals with cardiovascular diseases using the methods of artificial neural networks (ANN) is proposed. Classification of cardiocycles of electrocardiosignals based on features sets is realized using the radial basis neural network. The base architechture of networks based on radial basis functions is assumed the presence of three layers which executes various functions. In this work radial basis neural network is trained with 1000 data sets and tested with 1376 data sets.

Download PDF

Keywords Classification; cardiocycle; electrocardiosignal and radial basis neural network.
References 1. Зо Зо Тун, Филист С.А., Горбатенко С.А. Программный модуль для кодирования QRS-комплексов на основе морфологических признаков // Биомедицинская радиоэлектроника. – 2010. – № 2. – C. 24-29.
2. Осовский С. Нейронные сети для обработки информации / Пер. с польского И.Д. Рудинского. – М.: Финансы и статистика, 2002. – 344 с.
3. Хайкин Саймон. Нейронные сети: полный курс: Пер. с англ. – 2-е изд., испр. – М.: OOO “И.Д. Вильямс”, 2006. – 1104 с.
4. Howard Demuth, Mark Beale, Martin Hagan. Neural Network Toolbox User’s Guide for use with MATLAB, c COPYRIGHT 1992-2006 by The MathWorks, Inc. 848p.
5. Rajendra Acharya U, Jasjit S. Suri, Jos A.E. Spaan, Krishan S.M. Advances in cardiac signal processing, Springer-Verlag Berlin Heidelberg, 2007. – 478 p.

Comments are closed.