Comparative analysis of MABC with KNN, SOM, and ACO algorithms for ECG heartbeat classification

Selim Di̇lmaç,Zümray Dokur,Tamer Ölmez

doi:10.3906/elk-1712-328

Abstract

In this paper, we proposed a classification method based on a nature-inspired algorithm, i.e., modified artificial bee colony (MABC). This method was applied to electrocardiogram (ECG) heartbeat classification. ECG data was obtained from MITBIH database. Eight different types of heartbeats (N, j, V, F, f, A, a, and R) were analyzed. For a better classification result, both time domain and frequency domain features were used. Feature selection was done by divergence analysis. MABC classification accuracy and heartbeat sensitivity values were compared with the results of other methods. Among other classifiers, k-nearest neighbor (KNN), Kohonen's self-organizing map (SOM), and ant colony optimization (ACO) were the best performing ones, and therefore their results are presented. The MABC classifier achieved 97.18 % accuracy on the analyzed dataset, as well as high sensitivity values for heartbeat types.

Highlights

Electrocardiogram (ECG) is a record of heart’s electrical activity
Nature-inspired algorithms may imitate a process in nature or may use an approach simulating some intelligent behaviors of social animal groups in nature such as bird flocks and ant or bee colonies
In this study, the developed classification software based on the modified artificial bee colony (MABC) algorithm was executed on a computer which has 2.53 GHz Intel Core i5 processor and 3 GB RAM

Summary

Introduction

Electrocardiogram (ECG) is a record of heart’s electrical activity. Most of the cardiac disorders, called arrhythmia, may appear anytime during a day. Computer-aided, automated electrocardiographic signal analysis for arrhythmia classification has been an active research topic for the last couple of decades. For this purpose, various methods are used in the literature including linear and nonlinear classifiers [1,2,3,4,5,6,7,8,9]. Nature-inspired algorithms may imitate a process in nature or may use an approach simulating some intelligent behaviors of social animal groups in nature such as bird flocks and ant or bee colonies These kinds of algorithms are called swarm intelligence (SI) algorithms

Methods

Results

Conclusion