ECG Signal Feature Extraction and SVM Classifier Based Cardiac Arrhythmia Detection

Abstract

In a variety of medical applications, electrocardiogram (ECG) records are essential for the identification of cardiovascular disorders. Cardiovascular issues such cardiac arrhythmias and coronary heart disease (CHD) are among the most prevalent and can result in cardiac arrest or sudden cardiac death. This study employs ECG signal preprocessing and feature extraction to identify cardiac arrhythmias and evaluate CHD risk. This research stresses the use of a Support Vector Machine (SVM) classifier for cardiac arrhythmia identification after ECG signal preprocessing. The preprocessed ECG signal is then subjected to arrhythmic beat classification to find anomalies. Extracted R-peaks from the ECG signal are divided into normal and arrhythmic risk subjects using the SVM classification-based approach for abnormality identification. When compared to other similar classifiers, the K-Nearest Neighbor (KNN) classifier offers the highest classification accuracy of 97.5%.