ECG Beats Classification Using Multi-class Sparse Linear Classifiers

Abstract

A feature selection technique based on mathematical programming that results in a robust classifier is presented for classification of electrocardiogram (ECG) beats. The classifier depends only on a small subset of numerical feature extracted from original data. Multi-class problem is converted to the binary issue by Relative Difference space (RDS) method. We verify the robustness of our method on six types of ECG beats obtained from the MIT-BIH database. The present research demonstrates that the multi-class sparse linear classifier can achieves high classification accuracies.