ECG images classification using artificial neural network based on several feature extraction methods
Mazhar Basyouni Tayel, Mohamed E. El-Bouridy · 2008
This paper, presents an intelligent diagnosis system for electrocardiogram (ECG) intensity images using artificial neural network (ANN). Features are extracted from many preprocess such as wavelet decomposition (WD), Edge detection (ED), gray level histogram (GLH), Fast Fourier transform (FFT), and Mean-variance (M-V). The ANN supervised feed-forward back propagation using adaptive learning rate with momentum term algorithm used as a classifier. The input data to the classifier is very large so, ECG images data are grouped in batches that introduced to ANN classifier. The objective of this paper is to introduce an expert system for ECG diagnosis, more suitable preprocess for the used 63 ECG intensity images, and simplest ANN architecture classifier, depending on the higher accuracy of the classifier related to the extracted input features.