A Technique for Classifying the ECG Signal into Various Possible States of the Cardiovascular System

Abstract

A technique for automatic determination of the states of the cardiovascular system based on recorded ECG signals based on artificial neural networks is proposed. To achieve this, an artificial neural network must be trained to classify signals into various possible states of the body. Therefore, heart rate variability (HRV) parameters are extracted from ECG signals and used as input functions for the neural network. The structure of the classifier, the architecture of the neural network and the method for obtaining the necessary parameters in the learning process are presented. Finally, the effectiveness of the qualification process is checked and the proposed classifier is evaluated.