Authors : Vineesha N. B.; B. Umabharathi; Mary Sandra

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/3duts3hr

Scribd : https://tinyurl.com/mrywtpd2

DOI : https://doi.org/10.38124/ijisrt/26apr1537

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Abstract: This study aims at detecting cardiac arrhythmia which is found in a large population today because of the hypertension and lifestyle. When heart beat is irregular in a human being we can all that as cardiac arrhythmia. Cardiac diseases are a major reason of less life expectancy and so it is a crucial and severe health problem in today’s era. A framework based on Conventional neural network and BiLSTM-Bidirectional Long Short Term Memory networks are using here to classify the ECG signals and to detect Cardiac arrhythmia. Since ECG signals are time-series signals, this hybrid model is one of the best. CNN has different layers and through different steps CNN will do feature extraction while BiLSTM will capture long-term dependencies in ECG Signals, temporal frequencies in the heartbeat. ECG signals are classified and it will give the ouput as - Normal, Low risk, high risk. So CNN + BiLSTM together will work and detect abnormalities in ECG waveforms, learns heartbeat sequence and classify accurately thereby detect Cardiac arrhythmia earlier.

Keywords : Cardiac Arrhythmia Detection, Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), Time-Series Signal Analysis, ECG Classification.

References :

1. P. N. Aarotale and A. Rattani, “Deep learning models for arrhythmia classification using stacked time-frequency scalogram images from ECG signals,” Conference/Journal Paper, 2025.
2. S. Anusya and K. P. Rajesh, “Heartbeat ECG recognition method for arrhythmia classification via machine learning algorithm,” Journal of Neonatal Surgery, vol. 14, no. 4s, 2025.
3. A. Sharma and R. Gupta, “Arrhythmia classification using deep learning techniques,” International Journal of Advanced Computer Science and Applications.
4. M. Patel and S. Verma, “Automated ECG arrhythmia detection using CNN,” IEEE Conference on Biomedical Engineering.
5. P. Kumar and L. Singh, “Machine learning-based ECG signal classification,” International Journal of Engineering Research.
6. R. Mehta and S. Iyer, “Hybrid deep learning model for cardiac arrhythmia detection,” IEEE Access.
7. K. Reddy and M. Rao, “Real-time ECG arrhythmia detection using ANN,” International Conference on Healthcare Informatics.
8. V. Nair and A. Joseph, “ECG signal classification using support vector machine,” Journal of Medical Systems.
9. T. Das and P. Chakraborty, “Deep CNN for multi-class arrhythmia detection,” Biomedical Signal Processing and Control.
10. S. Khan and M. Ali, “Ensemble learning for ECG-based heart disease prediction,” International Journal of Biomedical Engineering.
11. D. Mishra and R. Tiwari, “LSTM-based arrhythmia detection model,” IEEE International Conference on AI in Healthcare.
12. A. Bose and N. Saha, “ECG feature extraction and classification using random forest,” Procedia Computer Science.
13. S. Narayan and P. Kulkarni, “Intelligent system for arrhythmia detection using deep neural networks,” Journal of Healthcare Engineering.
14. J. Thomas and R. Mathew, “Wavelet transform-based ECG classification,” International Journal of Signal Processing.
15. M. Gupta and S. Kapoor, “Automated cardiac abnormality detection using AI,” IEEE Transactions on Biomedical Engineering.
16. L. Fernandes and P. D’Souza, “ECG beat classification using transfer learning,” Computers in Biology and Medicine.
17. Y. Wang and H. Li, “Multi-class ECG classification using deep residual network,” IEEE Access.
18. S. Roy and K. Banerjee, “Machine learning techniques for early detection of arrhythmia,” International Journal of Computer Applications.
19. R. Sharma and V. Malhotra, “Smart ECG monitoring system using IoT and AI,” International Conference on Smart Healthcare Systems.
20. N. Prakash and T. Srinivasan, “Deep hybrid model for cardiac arrhythmia prediction,” Expert Systems with Applications.