A Novel Deep 2D-CNN Model for ECG-Based Arrhythmia Diagnosis with Selective Attention Mechanism and CWT Integration

Hassanain Shakir Mansour; Morteza Valizadeh; Alaa Hussein Abdulaal; Mehdi Chehel Amirani

doi:10.30572/2018/KJE/160225

Authors

Hassanain Shakir Mansour Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, Urmia University, West Azerbaijan, Iran
Morteza Valizadeh Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, Urmia University, West Azerbaijan, Iran
Alaa Hussein Abdulaal Department of Electrical Engineering, College of Engineering, Al-Iraqia University, Baghdad, Iraq https://orcid.org/0000-0003-2316-2822
Mehdi Chehel Amirani Department of Electrical Engineering, Faculty of Electrical and Computer Engineering, Urmia University, West Azerbaijan, Iran

DOI:

https://doi.org/10.30572/2018/KJE/160225

Keywords:

Arrhythmia, ECG signals, CNN, Continuous wavelet transform, Selective attention mechanism

Abstract

This study introduces an innovative approach for arrhythmia diagnosis via electrocardiogram (ECG) signals, employing a 2D Convolutional Neural Network (CNN) model fused with a Continuous Wavelet Transform (CWT) and a Selective Attention Mechanism (SAM). The SAM enhances feature focus, improving classification accuracy. The model effectively categorizes ECG signals into Normal and Abnormal classes, subcategorizing Abnormal patterns into four types. Merging deep learning with signal processing enables the correct classification of arrhythmia. The outcome yields high accuracy, such as 99.784% for multi-class and 99.94% for binary classification. The methodology proposed in this paper shows the capability of secure yielding for arrhythmia diagnosis, setting novel standards within healthcare applications.

Downloads

Download data is not yet available.

References

Abdulaal, A. H, M. Valizadeh, Yassin, R. A., Albaker, B. M., Abdulwahhab, A. H., Amirani, M. C, & Shah, S. (2024d). Unsupervised histopathological sub-image analysis for breast cancer diagnosis using variational autoencoders, clustering, and supervised learning. Journal of Engineering and Sustainable Development, 28(6), 729–744.

Abdulaal, A. H., Yassin, R. A., Valizadeh, M., Abdulwahhab, A. H., Jasim, A. M., Mohammed, A. J., Jabir, H. J., Albaker, B. M., Dheyaa, N. H., & Amirani, M. C. (2024e). Cutting-Edge CNN approaches for breast histopathological classification: The impact of spatial attention mechanisms. ShodhAI: Journal of Artificial Intelligence, 1(1), 109–130.

Abdulaal, A.H., Dheyaa, N.H., Abdulwahhab, A.H., Yassin, R.A., Valizadeh, M., Albaker, B.M. and Mustaf, A.S. (2024a). Deep Learning-based Signal Identification in Wireless Communication Systems: a Comparative Analysis on 3G, LTE, and 5G Standards. Al-Iraqia Journal for Scientific Engineering Research , 3(3), pp.66–70.

Abdulaal, A.H., Valizadeh, M., Albaker, B.M., Yassin, R.A., Amirani, M.C. and Shah, A.F.M.S. (2024b). Enhancing Breast Cancer Classification Using a Modified GoogLeNet Architecture with Attention Mechanism. Al-Iraqia Journal of Scientific Engineering Research, 3(1).

Abdulaal, A.H., Valizadeh, M., Amirani, M.C. and Shahen Shah, A.F.M. (2024c). A self-learning Deep Neural Network for Classification of Breast Histopathological Images. Biomedical Signal Processing and Control, 87(Part B), p.105418.

Abdulwahhab, A.H., Alaa Hussein Abdulaal, Assad, Ali Abdulwahhab Mohammed and Morteza Valizadeh (2024). Detection of Epileptic Seizure Using EEG Signals Analysis Based on Deep Learning Techniques. Chaos, Solitons & fractals/Chaos, Solitons and Fractals, 181, pp.114700–114700.

Acharya, U.R., Fujita, H., Oh, S.L., Hagiwara, Y., Tan, J.H. and Adam, M. (2017). Application of Deep Convolutional Neural Network for Automated Detection of Myocardial Infarction Using ECG Signals. Information Sciences, 415-416, pp.190–198.

Ahmed, A.A., Ali, W., Abdullah, T.A.A. and Malebary, S.J. (2023). Classifying Cardiac Arrhythmia from ECG Signal Using 1D CNN Deep Learning Model. Mathematics, 11(3), p.562.

Ardeti, V.A., Kolluru, V.R., Varghese, G.T. and Patjoshi, R.K. (2023). An Overview on state-of-the-art Electrocardiogram Signal Processing methods: Traditional to AI-based Approaches. Expert Systems with Applications, 217, p.119561.

Asgharzadeh-Bonab, A., Amirani, M.C. and Mehri, A. (2020). Spectral Entropy and Deep Convolutional Neural Network for ECG Beat Classification. Biocybernetics and Biomedical Engineering, 40(2), pp.691–700.

Cheikhrouhou, O., Mahmud, R., Zouari, R., Ibrahim, M., Zaguia, A. and Gia, T.N. (2021). One-Dimensional CNN Approach for ECG Arrhythmia Analysis in Fog-Cloud Environments. IEEE Access, 9, pp.103513–103523.

Chen, C., Hua, Z., Zhang, R., Liu, G. and Wen, W. (2020). Automated Arrhythmia Classification Based on a Combination Network of CNN and LSTM. Biomedical Signal Processing and Control, 57, p.101819.

Degirmenci, M., Ozdemir, M.A., Izci, E. and Akan, A. (2021). Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks. IRBM, 43(5), pp.422–433.

Gaidai, O., Cao, Y. and Loginov, S. (2023). Global cardiovascular diseases death rate prediction. Current Problems in Cardiology, 48(5), p.101622.

Giancaterino, S., Urey, M.A., Darden, D. and Hsu, J.C. (2020). Management of Arrhythmias in Cardiac Amyloidosis. JACC: Clinical Electrophysiology, 6(4), pp.351–361.

Gutiérrez-Gnecchi, J.A., Morfin-Magaña, R., Lorias-Espinoza, D., Tellez-Anguiano, A. del C., Reyes-Archundia, E., Méndez-Patiño, A. and Castañeda-Miranda, R. (2017). DSP-based Arrhythmia Classification Using Wavelet Transform and Probabilistic Neural Network. Biomedical Signal Processing and Control, 32, pp.44–56.

Hao, W., Yizhou, W., Yaqin, L. and Zhili, S. (2020). The Role of Activation Function in CNN. 2020 2nd International Conference on Information Technology and Computer Application (ITCA).

Huang, J., Chen, B., Yao, B. and He, W. (2019). ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network. IEEE Access, 7, pp.92871–92880.

Janssens, A.C.J.W. and Martens, F.K. (2020). Reflection on Modern methods: Revisiting the Area under the ROC Curve. International Journal of Epidemiology, 49(4), pp.1397–1403.

Li, D., Zhang, J., Zhang, Q. and Wei, X. (2017). Classification of ECG Signals Based on 1D Convolution Neural Network. 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom).

Liu, Z., Chen, Y., Zhang, Y., Ran, S., Cheng, C. and Yang, G. (2023). Diagnosis of Arrhythmias with Few Abnormal ECG Samples Using metric-based Meta Learning. Computers in Biology and Medicine, 153, pp.106465–106465.

Martis, R.J., Acharya, U.R., Mandana, K.M., Ray, A.K. and Chakraborty, C. (2013). Cardiac Decision Making Using Higher Order Spectra. Biomedical Signal Processing and Control, 8(2), pp.193–203.

Mathur, P., Srivastava, S., Xu, X. and Mehta, J.L. (2020). Artificial Intelligence, Machine Learning, and Cardiovascular Disease. Clinical Medicine Insights: Cardiology, 14, p.117954682092740.

Mohammed, H. A., Kareem S. W., & Mohammed A. S. (2022). A comparative evaluation of deep learning methods in digital image classification. Kufa Journal of Engineering, 13(4), 53–69.

Mohonta, S.C., Motin, M.A. and Kumar, D.K. (2022). Electrocardiogram Based Arrhythmia Classification Using Wavelet Transform with Deep Learning Model. Sensing and Bio-Sensing Research, 37, p.100502.

Moody, G.B. and Mark, R.G. (2001). The Impact of the MIT-BIH Arrhythmia Database. IEEE Engineering in Medicine and Biology Magazine, 20(3), pp.45–50.

Myrovali E., Tachmatzidis D, Antoniadis, A., & Vassilikos V. (2022). Identifying patients with paroxysmal atrial fibrillation from sinus rhythm ECG using random forests. Expert Systems with Applications, 213(Part A), 118948–118948.

Olanrewaju, R.F., Ibrahim, S.N., Asnawi, A.L. and Altaf, H. (2021). Classification of ECG Signals for Detection of Arrhythmia and Congestive Heart Failure Based on Continuous Wavelet Transform and Deep Neural Networks. Indonesian Journal of Electrical Engineering and Computer Science, 22(3), p.1520.

Pandey, S.K. and Janghel, R.R. (2020). Automatic Arrhythmia Recognition from Electrocardiogram Signals Using Different Feature Methods with Long short-term Memory Network Model. Signal, Image and Video Processing, 14.

Talib, M., Abdullah, A. A., K. Abdullah, A., & Bahaa, B. (2020). Twin fetus ECG signal extraction based on temporal predictability. Kufa Journal of Engineering, 11(1), 35–51.

Ullah, A., Anwar, S.M., Bilal, M. and Mehmood, R.M. (2020). Classification of Arrhythmia by Using Deep Learning with 2-D ECG Spectral Image Representation. Remote Sensing, 12(10), p.1685.

Ullah, A., Rehman, S. ur, Tu, S., Mehmood, R.M., Fawad and Ehatisham-ul-haq, M. (2021a). A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal. Sensors, 21(3), p.951.

Ullah, W., Siddique, I., Zulqarnain, R.M., Alam, M.M., Ahmad, I. and Raza, U.A. (2021b). Classification of Arrhythmia in Heartbeat Detection Using Deep Learning. Computational Intelligence and Neuroscience, 2021, pp.1–13.

Wang, Y., Yang, G., Li, S., Li, Y., He, L. and Liu, D. (2023). Arrhythmia Classification Algorithm Based on multi-head self-attention Mechanism. Biomedical Signal Processing and Control, 79, pp.104206–104206.

Yared Daniel Daydulo, Bheema Lingaiah Thamineni and Ahmed Ali Dawud (2023). Cardiac Arrhythmia Detection Using Deep Learning Approach and Time Frequency Representation of ECG Signals. BMC Medical Informatics and Decision Making, 23(1).

Yıldırım, Ö., Pławiak, P., Tan, R.-S. and Acharya, U.R. (2018). Arrhythmia Detection Using Deep Convolutional Neural Network with Long Duration ECG Signals. Computers in Biology and Medicine, 102, pp.411–420.