Arrhythmia Detection using Mutual Information-Based Integration Method

TL;DR

This paper introduces a novel mutual information-based ensemble method for ECG arrhythmia classification, achieving high accuracy by integrating multiple classifiers trained on the MIT-BIH database.

Contribution

The paper presents a new ensemble approach using mutual information for arrhythmia detection, demonstrating improved accuracy over traditional methods.

Findings

Ensemble accuracy reached 98.25%.

Mutual information-based integration outperformed majority voting.

Method applied successfully to MIT-BIH arrhythmia data.

Abstract

The aim of this paper is to propose an application of mutual information-based ensemble methods to the analysis and classification of heart beats associated with different types of Arrhythmia. Models of multilayer perceptrons, support vector machines, and radial basis function neural networks were trained and tested using the MIT-BIH arrhythmia database. This research brings a focus to an ensemble method that, to our knowledge, is a novel application in the area of ECG Arrhythmia detection. The proposed classifier ensemble method showed improved performance, relative to either majority voting classifier integration or to individual classifier performance. The overall ensemble accuracy was 98.25%.