Identification of Important Features In Detecting Arrhythmia by Using Penalized Support Vector Machine: Array

The electrocardiogram (ECG) is a diagnostic tool that is routinely used to assess the electrical and muscular functions of the heart. The electrocardiogram can measure the rate and rhythm of the heartbeat especially for Arrhythmia (irregular heartbeat), as well as provide indirect evidence of blood flow to the heart muscle. However, the existence of noise in ECG and variation of the Arrhythmia pattern make it difficult to identify important features of ECG and identified the type of Arrhythmia which leads to inconsistent classification performance of ECG. Therefore, this study aims to identify important features in ECG in detecting Arrhythmia by using penalized  SVM. This paper demonstrates how datasets obtained from the University of California at Irvine (UCI) Cardiac Arrhythmias Database are used to classify the using penalized SVM. Finally, the results obtain is The accuracy of the features C is the highest (0.841) compare with other features which show that QRS Duration, PR Interval, QT Interval, QRST and sex attribute are the important features of ECG that help in detecting Arrhythmia.