Hybrid Time-Frequency ECG Arrhythmia Classification with Feature-Model Compatibility and Ensemble Decision Fusion
Abstract
Cardiac arrhythmia is a critical cardiovascular disorder associated with high global mortality, while electrocardiogram (ECG)-based diagnosis remains time-consuming and susceptible to inter-observer variability. Although recent artificial intelligence approaches have improved automated ECG analysis, many existing studies rely on single time-frequency representations and uniform classification strategies, limiting their ability to capture complementary ECG characteristics. This study proposed a hybrid time-frequency ECG arrhythmia classification framework incorporating feature–model compatibility and ensemble decision fusion to improve classification robustness and reliability. ECG signals from the MIT-BIH Arrhythmia Database were preprocessed using a fourth-order Butterworth bandpass filter and segmented using overlapping windows. To prevent data leakage, patient-wise cross-validation was employed, ensuring that ECG segments originating from the same patient were assigned exclusively to either training or testing folds. Three complementary time-frequency representations, namely Mel-Spectrogram, Short-Time Fourier Transform (STFT), and Discrete Wavelet Transform (DWT), were paired with their most compatible classifiers: Convolutional Neural Network (CNN); Random Forest (RF); and Support Vector Machine (SVM); respectively. Decision fusion was performed using stacking, hard voting, and soft voting strategies. Experimental results showed that the DWT-SVM model with stacking achieved the best overall performance, attaining 94.82% accuracy and a 94.59% F1-score, while STFT-RF with hard voting achieved comparable performance with 94.75% accuracy and a 94.50% F1-score. In contrast, Mel-Spectrogram-CNN produced substantially lower performance with 81.45% accuracy, indicating limited suitability of Mel-scale representations for ECG morphology analysis. Statistical analysis confirmed significant performance differences among models (p < 0.001). The findings demonstrate that integrating hybrid time-frequency representations with feature–model compatibility and model-dependent decision fusion provides a robust framework for automated ECG arrhythmia classification with strong potential for clinical decision support and real-time cardiac monitoring applications
Downloads
References
V. R. Netala, S. K. Teertam, H. Li, and Z. Zhang, “A Comprehensive Review of Cardiovascular Disease Management: Cardiac Biomarkers, Imaging Modalities, Pharmacotherapy, Surgical Interventions, and Herbal Remedies,” Sep. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/cells13171471.
H. Velandia, A. Pardo, M. I. Vera, and M. Vera, “Systematic Review of Artificial Intelligence and Electrocardiography for Cardiovascular Disease Diagnosis,” Bioengineering, vol. 12, no. 11, 2025, doi: 10.3390/bioengineering12111248.
N. Katal, S. Gupta, P. Verma, and B. Sharma, “Deep-Learning-Based Arrhythmia Detection Using ECG Signals: A Comparative Study and Performance Evaluation,” Diagnostics, vol. 13, no. 24, 2023, doi: 10.3390/diagnostics13243605.
M. R. Khan, Z. M. Haider, J. Hussain, F. H. Malik, I. Talib, and S. Abdullah, “Comprehensive Analysis of Cardiovascular Diseases: Symptoms, Diagnosis, and AI Innovations,” Bioengineering, vol. 11, no. 12, 2024, doi: 10.3390/bioengineering11121239.
A. J. Prakash and M. Atef, “A lightweight deep learning approach for patient-specific electrocardiogram beat classification using local and long-term dependencies,” Eng. Appl. Artif. Intell., vol. 152, p. 110754, 2025, doi: https://doi.org/10.1016/j.engappai.2025.110754.
E. H. Houssein, H. Mostafa, A. A. Ali, H. Shaban, and M. S. Hassanein, “Advances in artificial intelligence techniques for diagnosis of cardiac diseases,” Discover Artificial Intelligence, vol. 6, no. 1, p. 424, 2026, doi: 10.1007/s44163-026-01323-y.
Z. Wu and C. Guo, “Deep learning and electrocardiography: systematic review of current techniques in cardiovascular disease diagnosis and management,” Biomed. Eng. Online, vol. 24, no. 1, p. 23, 2025, doi: 10.1186/s12938-025-01349-w.
M. Melinda, M. Raja, J. Junidar, R. Miftahujjannah, S. Rusdiana, and M. Irhamsyah, “Performance Comparison Analysis of Random Forest, Support Vector Machine, and AdaBoost in Arrhythmia Classification,” Journal of Image and Graphics (United Kingdom), vol. 13, no. 5, pp. 540–548, 2025, doi: 10.18178/JOIG.13.5.540-548.
L. C. Nechita et al., “AI-Enhanced ECG Applications in Cardiology: Comprehensive Insights from the Current Literature with a Focus on COVID-19 and Multiple Cardiovascular Conditions,” Diagnostics, vol. 14, no. 17, 2024, doi: 10.3390/diagnostics14171839.
D. Al-Shammary, M. Radhi, A. H. AlSaeedi, A. M. Mahdi, A. Ibaida, and K. Ahmed, “Efficient ECG classification based on the probabilistic Kullback-Leibler divergence,” Inform. Med. Unlocked, vol. 47, p. 101510, 2024, doi: https://doi.org/10.1016/j.imu.2024.101510.
Y. Liu et al., “Y-Net-ECG: A Multi-Lead informed and interpretable architecture for ECG segmentation across diverse rhythms,” Expert Syst. Appl., vol. 283, p. 127955, 2025, doi: https://doi.org/10.1016/j.eswa.2025.127955.
M. Fira, L. Goraș, L. Fira, R. F. Popa, and H.-N. Costin, “Arrhythmia Classification with Single-Channel Features Extracted from ‘A Large-Scale 12-Lead ECG Database for Arrhythmia Study,’” Sensors, vol. 25, no. 18, 2025, doi: 10.3390/s25185621.
E. Oporto, D. Mauricio, N. Maculan, and G. Uribe, “Challenges in the Classification of Cardiac Arrhythmias and Ischemia Using End-to-End Deep Learning and the Electrocardiogram: A Systematic Review,” Diagnostics, vol. 16, no. 1, 2026, doi: 10.3390/diagnostics16010161.
A. Eleyan, F. Bayram, and G. Eleyan, “Spectrogram-Based Arrhythmia Classification Using Three-Channel Deep Learning Model with Feature Fusion,” Applied Sciences, vol. 14, no. 21, 2024, doi: 10.3390/app14219936.
Y. Yunidar, M. Melinda, Albahri, H. Aulia, H. Dimiati, and N. Basir, “Precise Electrocardiogram Signal Analysis Using ResNet, DenseNet, and XceptionNet Models in Autistic Children,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, vol. 7, no. 4, pp. 1303–1319, Oct. 2025, doi: 10.35882/jeeemi.v7i4.1044.
F. M. Heir, H. Najafzadeh, and S. Erfani, “A hybrid CNN and reinforcement learning framework for speaker identification using Mel-Spectrogram and continuous wavelet transform features,” Sci. Rep., vol. 16, no. 1, Dec. 2026, doi: 10.1038/s41598-026-35858-y.
J. Rahul and L. D. Sharma, “Advancements in AI for cardiac arrhythmia detection: A comprehensive overview,” Comput. Sci. Rev., vol. 56, p. 100719, 2025, doi: https://doi.org/10.1016/j.cosrev.2024.100719.
A. A. Mohammed et al., “Enhanced arrhythmia diagnosis using a hybrid deep learning model: A CNN-LSTM-GRU approach on ECG data,” Biosens. Bioelectron. X, vol. 30, p. 100767, 2026, doi: https://doi.org/10.1016/j.biosx.2026.100767.
M. Qi, H. Shao, N. Shi, G. Wang, and Y. Lv, “Arrhythmia classification detection based on multiple electrocardiograms databases,” PLoS One, vol. 18, no. 9, pp. e0290995-, Sep. 2023, [Online]. Available: https://doi.org/10.1371/journal.pone.0290995
K. Gunasekaran, V. D. Ambeth Kumar, and M. J. A., “Artifact removal from ECG signals using online recursive independent component analysis,” Journal of Computational Mathematics and Data Science, vol. 13, p. 100102, 2024, doi: https://doi.org/10.1016/j.jcmds.2024.100102.
M. F. Safdar, R. M. Nowak, and P. Pałka, “Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review,” Comput. Biol. Med., vol. 170, p. 107908, Mar. 2024, doi: 10.1016/J.COMPBIOMED.2023.107908.
S. Lamba, S. Kumar, and M. Diwakar, “FADLEC: feature extraction and arrhythmia classification using deep learning from electrocardiograph signals,” Discover Artificial Intelligence, vol. 5, no. 1, p. 82, 2025, doi: 10.1007/s44163-025-00290-0.
C. Qiu, H. Li, C. Qi, and B. Li, “Enhancing ECG classification with continuous wavelet transform and multi-branch transformer,” Heliyon, vol. 10, no. 5, Mar. 2024, doi: 10.1016/j.heliyon.2024.e26147.
H. Bechinia, D. Benmerzoug, and N. Khlifa, “Approach Based Lightweight Custom Convolutional Neural Network and Fine-Tuned MobileNet-V2 for ECG Arrhythmia Signals Classification,” IEEE Access, vol. 12, pp. 40827–40841, 2024, doi: 10.1109/ACCESS.2024.3378730.
Y. Ye, K. Chipusu, M. A. Ashraf, B. Ding, Y. Huang, and J. Huang, “Hybrid CNN-BLSTM architecture for classification and detection of arrhythmia in ECG signals,” Sci. Rep., vol. 15, no. 1, p. 34510, 2025, doi: 10.1038/s41598-025-17671-1.
M. Irhamsyah, M. Melinda, J. Alifa, J. Prayoga, and Y. H. P. Iskandar, “ECG Atrial Fibrillation Signal Classification Method Based on Discrete Wavelet Transform (DWT) and DenseNet-121,” 2024 10th International Conference on Smart Computing and Communication, ICSCC 2024, pp. 619–624, 2024, doi: 10.1109/ICSCC62041.2024.10690792.
S. Dhyani, A. Kumar, and S. Choudhury, “Analysis of ECG-based arrhythmia detection system using machine learning,” MethodsX, vol. 10, p. 102195, Jan. 2023, doi: 10.1016/J.MEX.2023.102195.
J. Wang, J. Zang, S. Yao, Z. Zhang, and C. Xue, “Multiclassification for heart sound signals under multiple networks and multi-view feature,” Measurement, vol. 225, p. 114022, Feb. 2024, doi: 10.1016/J.MEASUREMENT.2023.114022.
M. Fakhry and A. Gallardo-Antolín, “A hybrid neural network with multistage feature fusion for detecting heart failure and murmurs from time–frequency representations of phonocardiograms,” Systems and Soft Computing, vol. 7, p. 200391, 2025, doi: https://doi.org/10.1016/j.sasc.2025.200391.
J. Prayoga, M. Melinda, T. Y. Arif, and H. Dimiati, “Comparison of Efficientnet B3 and Inception V3 Architecture Performance in Heart Disease Arrhythmia Image Classification,” International Conference on Computer and Communication Engineering, ICCCE, no. 2025, pp. 357–362, 2025, doi: 10.1109/ICCCE66530.2025.11474189.
M. Dehghanpour, M. Fateh, Z. Mohammadpoory, and S. Ferdowsi, “KhayyamNet: A Parallel Multiscale Feature Fusion Framework for Accurate Diagnosis of Multiple Sclerosis and Myelitis,” Mach. Learn. Knowl. Extr., vol. 8, no. 3, 2026, doi: 10.3390/make8030062.
Z. Xu and Z. Yu, “Maximizing Single-Feature Separability for Improving Transfer Learning in Motor Imagery EEG Decoding,” Brain Sci., vol. 16, no. 2, 2026, doi: 10.3390/brainsci16020230.
O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, pp. 6086-, Mar. 2024, doi: 10.1038/s41598-024-56706-x.
D. Wilimitis and C. G. Walsh, “Practical Considerations and Applied Examples of Cross-Validation for Model Development and Evaluation in Health Care: Tutorial,” JMIR AI, vol. 2, no. 1, 2023, doi: 10.2196/49023.
A. Alwakeel, M. Alwakeel, M. Hijji, T. J. Saleem, and S. R. Zahra, “Performance Evaluation of Different Decision Fusion Approaches for Image Classification,” Applied Sciences, vol. 13, no. 2, 2023, doi: 10.3390/app13021168.
F. Zhao et al., “Multi-classifier fusion based on belief-value for the diagnosis of autism spectrum disorder,” Front. Hum. Neurosci., vol. Volume 17-2023, 2023, doi: 10.3389/fnhum.2023.1257987.
S. U. Haq et al., “Reseek-Arrhythmia: Empirical Evaluation of ResNet Architecture for Detection of Arrhythmia,” Diagnostics, vol. 13, no. 18, 2023, doi: 10.3390/diagnostics13182867.
F. Fiel Peres, “Effect sizes for nonparametric tests,” Biochem. Med. (Zagreb)., vol. 36, no. 1, Feb. 2025, doi: 10.11613/BM.2026.010101.
F. Zabihi, F. Safara, and B. Ahadzadeh, “An electrocardiogram signal classification using a hybrid machine learning and deep learning approach,” Healthcare Analytics, vol. 6, p. 100366, 2024, doi: https://doi.org/10.1016/j.health.2024.100366.
C. N. Nurbadriani, M. Melinda, Y. Yunidar, and F. Arnia, “Electrocardiogram Detection System of Autistic Children Based on AD8232 for Healthcare,” Proceeding - 2023 2nd International Conference on Computer System, Information Technology, and Electrical Engineering: Sustainable Development for Smart Innovation System, COSITE 2023, pp. 126–131, 2023, doi: 10.1109/COSITE60233.2023.10250117.
Copyright (c) 2026 J Prayoga, Melinda Melinda, Teuku Yuliar Arif, Herlina Dimiati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
