Detection of Myocardial Infarction from Electrocardiography Signals with Multiscale Principal Component Analysis and Convolutional Neural Networks

Myocardial Infarction is a vital disease that needs to be intervened in very short time. The analysis of the patient's electrocardiography (ECG) data has an important place diagnosis. For this reason, computer aided decision support systems have been used recent years order determine more quickly and accurately. In study, classification was made using convolutional neural network algorithms on ECG signals obtained from 61 patients diagnosed with myocardial infarction 52 healthy individuals. are preprocessed three different filters by applying finite impulse response (FIR) filter, infinite (IIR) filter multiscale principal component analysis. According results obtained, success achieved 92.3% accuracy multi-scale analysis, it seen successful performance compared help FIR, IIR filter.