Automatic detection of cardiac arrhythmias using wavelets, neural networks and particle swarm optimization

This paper presents the use of particle swarm optimization (PSO), Wavelets and neural networks for automatic detection of cardiac arrhythmias based on analysis of the electrocardiogram (ECG). The ECG signal is evaluated in time-frequency domain using wavelets. Wavelet coefficients are presented as the input of a multilayer perceptron (MLP) artificial neural network (ANN) with three layers, which is trained (optimization of the weights) by the PSO algorithm. Finally, the trained network was able to classify the ECG signal in normal signal, atrial fibrillation or ventricular tachycardia. The database utilized was the MIT-BIH Arrhythmia Database. The accuracy rate was 97.03%.