Reliable ECG Classification Using RNN and GRU Architectures for Arrhythmia Detection
Boletim da Sociedade Paranaense de Matemática · 07.10.2025 · 43 (3) · 1-10
DOI: 10.5269/bspm.78536 ↗Kurz gefasst
Fachartikel in der Zeitschrift Boletim da Sociedade Paranaense de Matemática, online erschienen am 07.10.2025. Verfasst von Bhagyashree Saikia und 3 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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 arrhythmias, potentially reducing morbidity and mortality associated with cardiovascular diseases. This study presents a comparative analysis of Recurrent Neural Network(RNN) and Grated Recurrent Unit(GRU) architectures for ECG signal 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.
Zitieren
APA
Saikia, B., Debbarma, P., Kumar, R., & Dixit, M. M. (2025). Reliable ECG Classification Using RNN and GRU Architectures for Arrhythmia Detection. Boletim da Sociedade Paranaense de Matemática, 43(3), 1-10. https://doi.org/10.5269/bspm.78536
Vancouver
Saikia B, Debbarma P, Kumar R, Dixit MM. Reliable ECG Classification Using RNN and GRU Architectures for Arrhythmia Detection. Boletim da Sociedade Paranaense de Matemática. 2025;43(3):1-10. doi:10.5269/bspm.78536
BibTeX
@article{Saikia2025,
author = {Saikia, Bhagyashree and Debbarma, Pooja and Kumar, Rajesh and Dixit, M. M.},
title = {Reliable ECG Classification Using RNN and GRU Architectures for Arrhythmia Detection},
journal = {Boletim da Sociedade Paranaense de Matemática},
year = {2025},
volume = {43},
number = {3},
pages = {1--10},
doi = {10.5269/bspm.78536}
}
EUVIMED