Reliable ECG Classification Using RNN and GRU Architectures for Arrhythmia Detection

Bhagyashree Saikia; Pooja  Debbarma; Rajesh  Kumar; M.M.  Dixit

doi:10.5269/bspm.78536

Bhagyashree Saikia North Eastern Regional Institute of Science and Technology
Pooja Debbarma Research Scholar
Rajesh Kumar North Eastern Regional Institute of Science and Technology
M.M. Dixit North Eastern Regional Institute of Science and Technology

Resumen

Cardiac disease has become a severe threat to public health as
it has become a leading cause of mortality in India. Electrocardiogram (ECG)
signal classification plays a pivotal role in early detection of cardiac arrhyth
mias, potentially reducing morbidity and mortality associated with cardiovas
cular diseases. This study presents a comparative analysis of Recurrent Neural
Network(RNN) and Grated Recurrent Unit(GRU) architectures for ECG sig
nal classification using the MIT-BIH Arrhythmia dataset. After preprocessing
and class balancing, both models were trained to classify five heartbeat types.
Experimental results show that GRU model achieved a significantly higher test
accuracy (98.61%) compared to the RNN (83.39%), demonstrating its potential
for real-time cardiac monitoring applications in diagnostic systems and wearable
devices.

Descargas

La descarga de datos todavía no está disponible.

Biografía del autor/a

Pooja Debbarma, Research Scholar

Department of Electronics and Communication Engineering, North Eastern Regional Institute of Science and Technology, Nirjuli-791109, Arunachal Pradesh, India

Rajesh Kumar, North Eastern Regional Institute of Science and Technology

Professor, Department of Electronics and Communication Engineering,North Eastern Regional Institute of Science and Technology, Nirjuli-791109, Arunachal Pradesh, India

M.M. Dixit, North Eastern Regional Institute of Science and Technology

Professor, Department of Mathematics, North Eastern Regional Institute of
Science and Technology, Nirjuli-791109, Arunachal Pradesh, India

Citas

[1] Mohammed B Abubaker and Bilal Babayi˘git. Detection of cardiovascular
diseases in ecg images using machine learning and deep learning methods.
IEEE transactions on artificial intelligence, 4(2):373–382, 2022.
[2] U Rajendra Acharya, Shankar M Krishnan, Jos AE Spaan, and Jasjit S Suri.
Advances in cardiac signal processing, volume 8. Springer, 2007.
[3] Yaqoob Ansari, Omar Mourad, Khalid Qaraqe, and Erchin Serpedin. Deep
learning for ecg arrhythmia detection and classification: an overview of
progress for period 2017–2023. Frontiers in Physiology, 14:1246746, 2023.
[4] Xinwen Liu, Huan Wang, Zongjin Li, and Lang Qin. Deep learning in ecg
diagnosis: A review. Knowledge-Based Systems, 227:107187, 2021.
[5] Htet Myet Lynn, Sung Bum Pan, and Pankoo Kim. A deep bidirectional
gru network model for biometric electrocardiogram classification based on
recurrent neural networks. Ieee Access, 7:145395–145405, 2019.
[6] Patrick Schwab, Gaetano C Scebba, Jia Zhang, Marco Delai, and Walter
Karlen. Beat by beat: Classifying cardiac arrhythmias with recurrent neural
networks. In 2017 computing in cardiology (CinC), pages 1–4. IEEE, 2017.
[7] Halla Sigurthorsdottir, J´erˆome Van Zaen, Ricard Delgado-Gonzalo, and
Mathieu Lemay. Ecg classification with a convolutional recurrent neural
network. In 2020 Computing in Cardiology, pages 1–4. IEEE, 2020.
[8] Shraddha Singh, Saroj Kumar Pandey, Urja Pawar, and Rekh Ram Janghel.
Classification of ecg arrhythmia using recurrent neural networks. Procedia
computer science, 132:1290–1297, 2018.
[9] G. Yao, X. Mao, N. Li, H. Xu, X. Xu, Y. Jiao, and J. Ni. Interpretation
of electrocardiogram heartbeat by CNN and GRU. Computational and Mathe
matical Methods in Medicine, 2021:6534942, 2021