Myocardial infarction detection using magnitude squared coherence and Support Vector Machine

Abstract

This paper presents Magnitude Squared coherence(MSC) technique and Support Vector Machines (SVM) using kernel function for the classification of Inferior Myocardial Infarction. The coherence function finds common frequencies between two signals and evaluate the similarity of the two signals. MSC technique uses Welch method for calculating PSD. For the detection of normal and IMI beats, MSC technique output values are given as the input features for the SVM classifier. Overall accuracy of SVM classifier is 99.3 percent. The data was collected from MIT/BIH PTB database.