Electrocardiogram Waveforms Diagnosis based on Wavelet Representation and SqueezeNet Model

Authors

Ahmed Mohammed Merza
University of Babylon, College of Engineering/ Al-Musayab, Department of Energy and Renewable Energies Engineering. University of Warith Al-Anbiyaa, College of Engineering, Department of Biomedical Engineering.
Hussein Tami Sim
Department of Physics, College of Science, University of Babylon, Babylon, Iraq. College of Dentistry, University of Hilla, Babylon. Iraq.
Lateef Abd Zaid Qudr
Department of Computer Techniques Engineering, Al-Safwa University College, Karbala, Iraq
DOI: https://doi.org/10.52549/ijeei.v13i2.5529
Download PDF
Published: 30-06-2025 • Issue: Vol. 13 No. 2: June 2025 • Section: Regular paper

Abstract

AArrhythmia is an irregular in a person's beating heart that can happen occasionally. Heart rhythm problems can have disastrous results and seriously endanger health. Visually analyzing ECG data might be complex due to its large amount of information. Designing an automated method to assess the massive amount of ECG data is crucial. This research shows continuous wavelet transform (CWT) and deep learning strategies to automate detection and classification processes to examine three different ECG signals: congestive heart failure (CHF), normal sinus rhythm (NSR), and arrhythmia (ARR). CWT converts ECG signals into scalogram images for noise reduction and feature extraction. In deep learning, the modified SqueezeNet is employed to recognize the output of CWT, which is produced by the input of the ECG data. The proposed technique achieved 83.3%, 100%, and 94.7% accuracy in detecting CHF, NSR, and ARR. A comprehensive approach for classifying arrhythmias has been proposed, in which scalogram pictures of ECG waves are trained using the SqueezeNet model. The outcomes are superior to other current techniques and will significantly reduce wrong diagnoses
Keywords: Hyperparameters; ECG; CWT; SqueezeNet; Transfer Learning

References

Takcı, Hidayet. "Invasive, Non-Invasive, Machine Learning, and Artificial Intelligence Based Methods for Prediction of Heart Failure." (2022).

Kwon, Joon-myoung, et al. "Artificial intelligence assessment for early detection of heart failure with preserved ejection fraction based on electrocardiographic features." European Heart Journal-Digital Health 2.1 (2021): 106-116.

Reddy, N. Satish Chandra, et al. "Classification and feature selection approaches by machine learning techniques: Heart disease prediction." International Journal of Innovative Computing 9.1 (2019).

Sannino, Giovanna, and Giuseppe De Pietro. "A deep learning approach for ECG-based heartbeat classification for arrhythmia detection." Future Generation Computer Systems 86 (2018): 446-455.

Olanrewaju, Rashidah Funke, et al. "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 (IJEECS) 12.1 (2021): 1520-1528.

Krishnakumar, S., et al. "Detection of Arrhythmia and Congestive Heart Failure Through Classification of ECG Signals Using Deep Learning Neural Network." 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA). IEEE, 2021.

Anbarasi, A., et al. "A modified deep learning framework for arrhythmia disease analysis in medical imaging using electrocardiogram signal." BioMed Research International 2022 (2022).

Amin, Syed Umar, et al. "Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion." Future Generation computer systems 101 (2019): 542-554.

Mahmud, Mufti, et al. "Applications of deep learning and reinforcement learning to biological data." IEEE transactions on neural networks and learning systems 29.6 (2018): 2063-2079.

Yildirim, Özal. "A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification." Computers in biology and medicine 96 (2018): 189-202.

Pandey, Saroj Kumar, and Rekh Ram Janghel. "Automated detection of arrhythmia from electrocardiogram signal based on new convolutional encoded features with bidirectional long short-term memory network classifier." Physical and Engineering Sciences in Medicine 44.1 (2021): 173-182.

Abdul-Zahra, Dalael Saad, et al. "Classification of EEG signal by using optimized Quantum Neural Network." Indonesian Journal of Electrical Engineering and Informatics (IJEEI) 9.4 (2021): 1008-1014.â€

Madan, Parul, et al. "A hybrid deep learning approach for ECG-based arrhythmia classification." Bioengineering 9.4 (2022): 152.

Jawad, Ali Talib, et al. "Electrocardiograph signal recognition using wavelet transform based on optimized neural network." International Journal of Electrical and Computer Engineering (IJECE) 12.5 (2022): 4944-4950.

Fu’adah, Yunendah Nur, and Ki Moo Lim. "Classification of Atrial Fibrillation and Congestive Heart Failure Using Convolutional Neural Network with Electrocardiogram." Electronics 11.15 (2022): 2456.

Panjaitan, Febriyanti, Siti Nurmaini, and Radiyati Umi Partan. "Accurate Prediction of Sudden Cardiac Death Based on Heart Rate Variability Analysis Using Convolutional Neural Network." Medicina 59.8 (2023): 1394.

Shi, Jiguang, et al. "Optimized Solutions of Electrocardiogram Lead and Segment Selection for Cardiovascular Disease Diagnostics." Bioengineering 10.5 (2023): 607.

Deepa, S. R., et al. "Precision Diagnostic Algorithm for Multisubtype Arrhythmia Classification." 2023 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE). IEEE, 2023..

Ullah, Hadaate, et al. "An automatic premature ventricular contraction recognition system based on imbalanced dataset and pre-trained residual network using transfer learning on ECG signal." Diagnostics 13.1 (2022): 87.

Alqudah, Ali Mohammad, et al. "ECG heartbeat arrhythmias classification: A comparison study between different types of spectrum representation and convolutional neural networks architectures." Journal of Ambient Intelligence and Humanized Computing (2022): 1-31.

A Li, Jia, et al. "A spatial pyramid pooling-based deep convolutional neural network for the classification of electrocardiogram beats." Applied Sciences 8.9 (2018): 1590.

Rahuja, Nitin, and Sudarshan K. Valluru. "A comparative analysis of deep neural network models using transfer learning for electrocardiogram signal classification." 2021 International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT). IEEE, 2021..

S Sowmya, S., and Deepa Jose. "Detecting anomalies in fetal electrocardiogram records using deep learning models." Journal of Intelligent & Fuzzy Systems Preprint (2023): 1-18.

Abubaker, Mohammed B., and Bilal BabayiÄŸit. "Detection of cardiovascular diseases in ECG images using machine learning and deep learning methods." IEEE Transactions on Artificial Intelligence 4.2 (2022): 373-382.

Ozaltin, Oznur, and Ozgur Yeniay. "A novel proposed CNN–SVM architecture for ECG scalograms classification." Soft Computing 27.8 (2023): 4639-4658.

Author Biographies

Ahmed Mohammed Merza
Ahmed Mohammed Merza was born in Babylon, Iraq. He received his B.S. and M.S. degrees from the University of Babylon, College of Engineering, Electrical Engineering, Iraq, in 2013 and 2016, respectively. Now, he is a Ph.D. student in the research stage at Islamic Azad University, Isfahan, Iran, in electrical engineering. He is currently a Lecturer at the Department of Biomedical Engineering, College of Engineering, University of Warith Al-Anbiyaa, Karbala, Iraq. His research interests include wireless sensor networks, wireless communication, and soft-switching interleaved DC/DC converters. Working at Babylon University, College of Engineering—Al-Mussayab, Department of Energy and Renewable Energies Engineering, and University of Warith Al-Anbiyaa, College of Engineering.
Hussein Tami Sim
Hussein Tami Sim was born in Babylon, Iraq, on July 5, 1986. He received a BSc in General Physics from Babylon University. He completed and received a master's degree in nuclear physics from the University of Babylon, Iraq. Currently a Ph.D. student (medical physics) at Erciyes University, Turkey. He is a lecturer in the Department of Dentistry and the Department of Prosthetic Dental Technology at Hilla University College, Babylon, Iraq. His research interests include the use of lasers (Low-Level Laser Therapy (LLLT)) in the treatment of oral problems (ulcers, cleft lip, gum disease, sensitivity of fillings). In addition to theoretical physics. He can be contacted at the email: husseint@hilla-unc.edu.iq.
Lateef Abd Zaid Qudr
Lateef Abd Zaid Qudr is an assistant professor at the Computer Technology Engineering Department at Alsafwa University College, Iraq. He received a bachelor’s degree in computer sciences from Mansour University College and a master’s and a PhD in computer sciences from Donetsk National Technical University, Ukraine. His research interests include WSN, cloud computing, and IoT.

Lateef Abd Zaid Qudr is an assistant professor at the Computer Technology Engineering Department at Alsafwa University College, Iraq. He received a bachelor’s degree in computer sciences from Mansour University College and a master’s and a PhD in computer sciences from Donetsk National Technical University, Ukraine. His research interests include WSN, cloud computing, and IoT.

How to Cite

[1]
A. Mohammed Merza, H. T. Sim, and L. Abd Zaid Qudr, “Electrocardiogram Waveforms Diagnosis based on Wavelet Representation and SqueezeNet Model”, IJEEI, vol. 13, no. 2, pp. 525–535, Jun. 2025, doi: 10.52549/ijeei.v13i2.5529.