Data acquisition for myocardial infarction classification based on wavelets and Neural Networks

Abstract

This paper shows an approach for ECG signal processing based on artificial neural networks ANN and transform domains (discrete wavelet transform DWT and Fourier transform FT). The neural networks NNs are introduced to solve different pattern recognition problems associated with ECG analysis. A Multi-Layer Perceptron Neural Network MLP-NN is used in the present work with Back Propagation BP algorithm to train the proposed network. The operation of a classification system based on DWT and FT was analyzed for diagnosing a set of real patterns (QRS interval of normal and MI disease) that were taken from many patients of MAC-1200 12 channel ECG system from two hospitals in Baghdad. An off-line method was then used for the extraction of ECG signals from ECG images papers by using special image processing techniques. The obtained accuracy for the WT-NN was 90%, whereas that for the FT-NN was 85%. The results showed WT-NN to be better for analyzing the nonstationary signals.