Arrhythmia Classification Using Nearest Neighbor Search with Principal Component Analysis

Abstract

Arrhythmia is currently classified by rate, mechanism, or duration, and many experts are using different techniques to classify arrhythmia. The present group of researchers have developed an automated method to select useful heartbeat features, which were then applied to a κ-nearest neighbor algorithm of arrhythmia classification. The arrhythmia dataset from the University of California, Irvine, Machine Learning Repository was applied to test the performance of our method, yielding a classification accuracy of 98%. Copyright is held by the author/owner(s).