Decision Making Algorithm through LVQ Neural Network for ECG Arrhythmias

Abstract

In this paper, learning vector quantization artificial neural network method was used for designing decision support system for Electrocardiogram (ECG) analysis. Four types of ECG patterns were chosen from the data obtained from ECG simulator device to be recognized, including Bradycardia, tachycardia, monomorphic preventricular contraction, myocardial infraction R-R interval, QRS complex duration, ST-segment slope change features were performed as the characteristic representation of the original ECG signals to be fed into the neural network models. LVQ network was trained and tested for ECG pattern recognition and the experimental results, performance graphs are plotted for varying number of samples. The LVQ network exhibited the best performance and reached an overall accuracy of 95.5% when. trained with 200 samples with learning rate at 0.9.