CNN Based ECG Dual Heart Beat Arrhythmia Detection

Pulapakura . Anishka; S S Vidya Balantrapu; Pithani Ranjith Manohar; Seelam Srinivas; Malaka Suresh

doi:10.36948/ijfmr.2026.v08i02.70736

CNN Based ECG Dual Heart Beat Arrhythmia Detection

Author(s)	Mr. Pulapakura . Anishka, S S Vidya Balantrapu, Pithani Ranjith Manohar, Seelam Srinivas, Malaka Suresh
Country	India
Abstract	Electrocardiogram (ECG) signals are crucial in the process of cardiac diagnosis as well as ongoing monitoring of health. However, achieving best performance is difficult due to factors such as large variations between patients, imbalanced heartbeat classes, and very subtle differences between certain abnormal beats. Although convolutional neural networks (CNNs) have become popular for ECG classification because of their strong ability to learn features, models based on singlebeat ECG representations often fail to capture important beattobeat information.To address these limitations, this work proposes a dualheartbeat CNNbased framework for ECG arrhythmia classification. Instead of analyzing each heartbeat independently, the method combines neighbouring heartbeats to capture both waveform characteristics and temporal relationships between beats. ECG signals are segmented around detected Rpeaks, and adjacent beats are transformed into twodimensional coupling matrices that serve as inputs to the CNN. In addition, a systematic training beat selection strategy is applied to improve learning for less frequent arrhythmia types.The proposed framework is evaluated using the MITBIH Arrhythmia Database following AAMIrecommended evaluation protocols. Performance is assessed using standard metrics such as sensitivity, precision, and overall accuracy. Experimental results show that the dualheartbeat CNN approach outperforms conventional single-beat CNN models, particularly in detecting supraventricular ectopic beats, where sensitivity improves by approximately 5%to12% while maintaining consistent performance for other heartbeat classes .The suggested approach offers an entirely automatic and stable ECG analysis framework that does not require manual feature eliciting or professional assistance.
Keywords	Electrocardiogram,Arrhythmia,DualHeartbeat Coupling, Convolutional Neural Network, Beat Segmentation
Field	Medical / Pharmacy
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-09
DOI	https://doi.org/10.36948/ijfmr.2026.v08i02.70736

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 1 Cover Page Vol 7 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

CNN Based ECG Dual Heart Beat Arrhythmia Detection

Share this