Multi-Scale Convolutional Neural Network with LSTM for Accurate ECG Beat Classification
DOI:
https://doi.org/10.64882/ijrt.v14.i3.1583Keywords:
Electrocardiogram (ECG), Arrhythmia Classification, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Deep Learning, Random Over Sampling, MIT-BIH Arrhythmia Database, Softmax Classifier, Healthcare, Artificial Intelligence.Abstract
Electrocardiogram (ECG) signal classification plays a vital role in the early diagnosis of cardiac arrhythmias by enabling the automatic identification of abnormal heartbeats. However, the nonlinear nature of ECG signals and the presence of imbalanced heartbeat classes make accurate classification a challenging task. This paper proposes a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) framework for automated ECG heartbeat classification using the MIT-BIH Arrhythmia Database. Initially, the ECG signals undergo preprocessing, including data validation, label conversion, and reshaping into one-dimensional sequences. To address the class imbalance problem, Random Over Sampling (ROS) is applied to generate a balanced training dataset. The proposed architecture employs three successive one-dimensional convolutional layers with batch normalization and max-pooling operations to extract discriminative morphological features from ECG waveforms. Subsequently, two stacked LSTM layers are utilized to capture the temporal dependencies and sequential characteristics of heartbeat signals. The extracted deep features are then processed through fully connected dense layers, while a Softmax classifier performs five-class heartbeat classification. The network is trained using the Adam optimizer with categorical cross-entropy loss, together with early stopping and adaptive learning-rate reduction to enhance convergence and reduce overfitting. Performance evaluation is carried out using the independent MIT-BIH test dataset based on accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrate that the proposed CNN–LSTM model achieves an overall classification accuracy of approximately 98%, outperforming conventional machine learning and standalone deep learning approaches in terms of robustness and generalization. The proposed framework provides an efficient and reliable computer-aided diagnosis system for accurate arrhythmia detection and has significant potential for real-time clinical monitoring and intelligent healthcare applications.
References
Eleyan, A., & Alboghbaish, E. (2024). Electrocardiogram signals classification using deep-learning-based incorporated convolutional neural network and long short-term memory framework. Computers, 13(2), 55.
Zeng, W., Su, B., Chen, Y., & Yuan, C. (2023). Arrhythmia detection using TQWT, CEEMD and deep CNN-LSTM neural networks with ECG signals. Multimedia Tools and Applications, 82(19), 29913-29941.
Begum, S. G., Priyadarshi, E., Pratap, S., Kulshrestha, S., & Singh, V. (2023). Automated detection of abnormalities in ECG signals using deep neural network. Biomedical Engineering Advances, 5, 100066.
Tiwari, S., Jain, A., Sapra, V., Koundal, D., Alenezi, F., Polat, K., ... & Nour, M. (2023). A smart decision support system to diagnose arrhythymia using ensembled ConvNet and ConvNet-LSTM model. Expert Systems with Applications, 213, 118933.
Ye, Y., Chipusu, K., Ashraf, M. A., Ding, B., Huang, Y., & Huang, J. (2025). Hybrid CNN-BLSTM architecture for classification and detection of arrhythmia in ECG signals. Scientific Reports, 15(1), 34510.
Pramukantoro, E. S., Amron, K., Wardhani, V., & Kamila, P. A. (2024). A study of inferencing ECG heartbeat classification based on CNN and LSTM on edge devices.
Mukhametkaly, A., Momynkulov, Z., Kurmanbekkyzy, N., & Omarov, B. (2023). Deep Conv-lstm network for arrhythmia detection using ECG data. International Journal of Advanced Computer Science and Applications, 14(9).
Alamatsaz, N., Tabatabaei, L., Yazdchi, M., Payan, H., Alamatsaz, N., & Nasimi, F. (2024). A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection. Biomedical Signal Processing and Control, 90, 105884.
Alharbi, N. S., Jahanshahi, H., Yao, Q., Bekiros, S., & Moroz, I. (2023). Enhanced classification of heartbeat electrocardiogram signals using a long short-term memory–convolutional neural network ensemble: Paving the way for preventive healthcare. Mathematics, 11(18), 3942.
Anbarasi, A., & Ravi, T. (2023). Detection and classification of arrhythmia type using hybrid model of LSTM with convolutional neural network. Applied Nanoscience, 13(5), 3435-3445.
Kuila, S., Dhanda, N., & Joardar, S. (2024). ECG signal classification using DEA with LSTM for arrhythmia detection. Multimedia Tools and Applications, 83(15), 45989-46016.
Sharma, L. D., Rahul, J., Aggarwal, A., & Bohat, V. K. (2023). An improved cardiac arrhythmia classification using stationary wavelet transform decomposed short duration QRS segment and Bi-LSTM network. Multidimensional Systems and Signal Processing, 34(2), 503-520.
Lim, J., Han, D., Nejad, M. P. S., & Chon, K. H. (2024). ECG classification via integration of adaptive beat segmentation and relative heart rate with deep learning networks. Computers in biology and medicine, 181, 109062.Nikandish, R., He, J., &
Heartbeat Classification on Wearable Devices. IEEE Journal of Biomedical and Health Informatics.
Satheeswaran, V., Chandrika, G. N., Mitra, A., Chowdhury, R., Kumar, P., & Glory, E. (2024). Deep Learning based classification of ECG signals using RNN and LSTM Mechanism. Journal of Electronics, Electromedical Engineering, and Medical Informatics, 6(4), 332-342.
Mary, G. A. A., Sathyasri, B., Murali, K., Prabhu, L. A. J., & Bharatha Devi, N. (2023). Electrocardiogram signal classification in an IoT environment using an adaptive deep neural networks. Neural Computing and Applications, 35(21), 15333-15342.
Xie, Y. L., & Lin, C. W. (2023). Imbalanced ectopic beat classification using a low-memory-usage CNN LMUEBCNet and correlation-based ECG signal oversampling. Mathematics, 11(8), 1833.
Khan, F., Yu, X., Yuan, Z., & Rehman, A. U. (2023). ECG classification using 1-D convolutional deep residual neural network. Plos one, 18(4), e0284791.
Vinay, N. A., Vidyasagar, K. N., Rohith, S., Pruthviraja, D., Supreeth, S., & Bharathi, S. H. (2024). An RNN-Bi LSTM based multi decision GAN approach for the recognition of cardiovascular disease (CVD) from heart beat sound: a feature optimization process. IEEE Access, 12, 65482-65502.
Karri, M., Annavarapu, C. S. R., & Pedapenki, K. K. (2023). A Real-Time Cardiac Arrhythmia Classification Using Hybrid Combination of Delta Modulation, 1D-CNN and Blended LSTM. Neural Process. Lett., 55(2), 1499-1526.
Chaitanya, M. K., & Sharma, L. D. (2024). Pre-trained Bi-LSTM model for automated classification of ventricular arrhythmias using 1-D and 2-D ECG. Bulletin of Electrical Engineering and Informatics, 13(4), 2485-2495.
Liu, F., Li, H., Wu, T., Lin, H., Lin, C., & Han, G. (2023). Automatic classification of arrhythmias using multi-branch convolutional neural networks based on channel-based attention and bidirectional LSTM. ISA transactions, 138, 397-407.
Gündüz, A. F., & Talu, M. F. (2023). Atrial fibrillation classification and detection from ECG recordings. Biomedical Signal Processing and Control, 82, 104531.
Rofar, N. A. N. A., Aziz, N. S., Apandi, Z. F. M., & Othman, W. R. W. (2026, March). Evaluation of CNN and LSTM Model Performance for Classifying ECG Arrhythmias in Noise-Stressed Environments. In 2026 5th Asia Conference on Algorithms, Computing and Machine Learning (CACML) (pp. 1-7). IEEE.
Mohammed, A. A., Al-Sulami, Z. A., Abd Zaid, M. M., Abduljabbar, Z. A., Aldarbandee, M., Jaber, H., ... & Neamah, H. A. (2026). Enhanced Arrhythmia Diagnosis Using a Hybrid Deep Learning Model: A CNN-LSTM-GRU Approach on ECG Data. Biosensors and Bioelectronics: X, 100767.
Pokharel, A., Dahal, S., Sapkota, P., & Chhetri, B. B. (2024). Electrocardiogram (ecg) based cardiac arrhythmia detection and classification using machine learning algorithms. arXiv preprint arXiv:2412.05583.
Varshini, S., & Dhanush, T. S. (2024, December). A Hybrid CNN-LSTM Model for Accurate Prediction of Cardiac Arrhythmia using ECG Signals. In 2024 3rd International Conference on Automation, Computing and Renewable Systems (ICACRS) (pp. 1360-1368). IEEE.
Soman, A., & Sarath, R. (2024). Optimization-enabled deep convolutional neural network with multiple features for cardiac arrhythmia classification using ECG signals. Biomedical Signal Processing and Control, 92, 105964.
Ahmed, A. A., Ali, W., Abdullah, T. A., & Malebary, S. J. (2023). Classifying cardiac arrhythmia from ECG signal using 1D CNN deep learning model. Mathematics, 11(3), 562.
Midani, W., Ouarda, W., & Ayed, M. B. (2023). DeepArr: An investigative tool for arrhythmia detection using a contextual deep neural network from electrocardiograms (ECG) signals. Biomedical Signal Processing and Control, 85, 104954.
Mohammad Kachuee, Shayan Fazeli, and Majid Sarrafzadeh. "ECG Heartbeat Classification: A Deep Transferable Representation." arXiv preprint arXiv:1805.00794 (2018).
Amhia, H., & Wadhwani, A. K. (2022). Stability and Phase Response Analysis of Optimum Reduced‐Order IIR Filter Designs for ECG R‐Peak Detection. Journal of Healthcare Engineering, 2022(1), 9899899.
Amhia, H., & Wadhwani, A. K. (2021). Designing an optimum and reduced order filter for efficient ECG QRS peak detection and classification of arrhythmia data. Journal of Healthcare Engineering, 2021(1), 6542290.
Amhia, H., Sarkar, V., Pandey, L. N., Shakunthala, M., Anudeep, S., & Singh, S. (2024, December). Advanced Algorithm for Cardiac Arrhythmia Classification and Efficient Detection of Abnormalities in ECG Signals. In 2024 IEEE 4th International Conference on ICT in Business Industry & Government (ICTBIG) (pp. 1-6). IEEE.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
