Adaptive Attention-Driven ALEXIS Framework for High-Precision ECG Signal Classification
Abstract
Accurate classification of electrocardiogram (ECG) signals is essential for the early identification of cardiac abnormalities and for supporting timely clinical decision-making. However, conventional machine learning and deep learning approaches often assume stationary signal characteristics and therefore struggle to model the complex non-linear, non-stationary, and patient-specific nature of ECG signals. These limitations reduce their ability to capture subtle morphological variations and temporal dependencies associated with abnormal cardiac rhythms. To address these challenges, this paper proposes an Adaptive Attention-Driven ALEXIS Framework, a hybrid deep learning architecture that integrates multiscale signal decomposition, hierarchical feature learning, and adaptive attention-guided fusion for five-class ECG abnormality classification. The proposed framework combines the Stockwell Transform (ST) for time-frequency analysis, Empirical Mode Decomposition (EMD) for adaptive extraction of intrinsic oscillatory modes, and Local Phase Quantization (LPQ) for robust morphological feature representation. The extracted multiscale features are processed through an AlexNet-based spatial learning module and an LSTM-based temporal modeling module, followed by an attention-guided feature fusion mechanism and Support Vector Machine (SVM) classifier for robust decision making. The framework was evaluated using the MIT-BIH Arrhythmia Database comprising 109,494 annotated ECG beats, which were partitioned into 80% training (approximately 87,595 beats) and 20% testing (approximately 21,899 beats) using a stratified beat-level split. Experimental evaluation on the independent test set achieved an overall accuracy of 98.43%, sensitivity of 98.27%, specificity of 98.78%, and F1-score of 98.31%. These results demonstrate that the proposed ALEXIS framework effectively captures complementary spectral, temporal, and morphological ECG characteristics, providing accurate and interpretable ECG abnormality classification while establishing a strong foundation for future validation using inter-patient evaluation protocols and cross-database clinical studies
Downloads
References
A. Abdellatif, H. Mubarak, H. Abdellatef, J. Kanesan, Y. Abdelltif, C. Chow, J. Huang Chuah, H. Muwafaq Gheni, and G. Kendall, “Computational detection and interpretation of heart disease based on conditional variational auto-encoder and stacked ensemble-learning framework,” Biomed. Signal Process. Control, vol. 88, Art. no. 105644, 2024. https://doi.org/10.1016/j.bspc.2023.105644
G. Tartarisco, G. Cicceri, R. Bruschetta, A. Tonacci, S. Campisi, S. Vitabile, A. Cerasa, S. Distefano, A. Pellegrino, P. A. Modesti, and G. Pioggia, “An intelligent Medical Cyber–Physical System to support heart valve disease screening and diagnosis,” Expert Syst. Appl., vol. 238, Art. no. 121772, 2024. https://doi.org/10.1016/j.eswa.2023.121772
Y. Hernández and J. Pérez, “A systematic review of machine learning and IoT applied to the prediction and monitoring of cardiovascular diseases,” Healthcare, vol. 11, no. 16, Art. no. 2240, 2023. https://doi.org/10.3390/healthcare11162240
R. Saini, N. Bindal and P. Bansal, "Classification of heart diseases from ECG signals using wavelet transform and kNN classifier," International Conference on Computing, Communication & Automation, Greater Noida, India, 2015, pp. 1208-1215, https://doi.org/10.1109/CCAA.2015.7148561
G. Kalpana, N. Deepa, and D. Dhinakaran, “Advanced image preprocessing and context-aware spatial decomposition for enhanced breast cancer segmentation,” MethodsX, vol. 14, Art. no. 103224, 2025. https://doi.org/10.1016/j.mex.2025.103224
M. Hammad, A. A. Abd El-Latif, A. Hussain, F. E. Abd El-Samie, B. B. Gupta, H. Ugail, and A. Sedik, “Deep learning models for arrhythmia detection in IoT healthcare applications,” Comput. Electr. Eng., vol. 100, Art. no. 108011, 2022. https://doi.org/10.1016/j.compeleceng.2022.108011
Y. Hagiwara, H. Fujita, S. L. Oh, J. H. Tan, R. S. Tan, E. J. Ciaccio, and U. R. Acharya, “Computer-aided diagnosis of atrial fibrillation based on ECG signals: A review,” Inf. Sci., vol. 467, pp. 99–114, 2018. https://doi.org/10.1016/j.ins.2018.07.063
D. Dhinakaran, L. Srinivasan, S. Edwin Raja, K. Valarmathi, and M. Gomathy Nayagam, “Synergistic feature selection and distributed classification framework for high-dimensional medical data analysis,” MethodsX, vol. 14, Art. no. 103219, 2025. https://doi.org/10.1016/j.mex.2025.103219
A. Brenyo and M. K. Aktas, “Review of complementary and alternative medical treatment of arrhythmias,” Am. J. Cardiol., vol. 113, no. 5, pp. 897–903, Mar. 2014. https://doi.org/10.1016/j.amjcard.2013.11.044
B. M. Asl, S. K. Setarehdan, and M. Mohebbi, “Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal,” Artif. Intell. Med., vol. 44, no. 1, pp. 51–64, 2008. https://doi.org/10.1016/j.artmed.2008.04.007
A. Al-Alshaikh, R. C. Poonia, A. K. Saudagar, M. Yadav, H. S. AlSagri, and A. A. AlSanad, “Comprehensive evaluation and performance analysis of machine learning in heart disease prediction,” Sci. Rep., vol. 14, no. 1, pp. 1–15, 2024. https://doi.org/10.1038/s41598-024-58489-7
L. Abualigah, D. Izci, M. Jabari, et al., “Adaptive Gbest-guided atom search optimization for designing stable digital IIR filters,” Circuits Syst. Signal Process., vol. 44, pp. 4059–4081, 2025. https://doi.org/10.1007/s00034-025-02997-y
C. J. Zhang, F. Q. Tang, H. P. Cai, and Y. F. Qian, “Heart failure classification using deep learning to extract spatiotemporal features from ECG,” BMC Med. Inform. Decis. Mak., vol. 24, Art. no. 17, 2024. https://doi.org/10.1186/s12911-024-02415-4
A. Eleyan and E. Alboghbaish, “Electrocardiogram signals classification using deep-learning-based incorporated convolutional neural network and long short-term memory framework,” Computers, vol. 13, no. 2, Art. no. 55, 2024. https://doi.org/10.3390/computers13020055
A. K. Dubey, A. K. Sinhal, and R. Sharma, “Heart disease classification through crow intelligence optimization-based deep learning approach,” Int. J. Inf. Technol., vol. 16, pp. 1815–1830, 2024. https://doi.org/10.1007/s41870-023-01445-x
A. Hussein, S. Alomari, M. Almomani, R. Zitar, H. Migdady, A. Smerat, V. Snasel, and L. Abualigah, “A hybrid PSO-GCRA framework for optimizing control systems performance,” Int. J. Robot. Control Syst., vol. 5, no. 1, pp. 459–478, 2025. https://doi.org/10.31763/ijrcs.v5i1.1738
C. Padmavathi and S. V. Veenadevi, “An automated embedded distribution of deep learning heart disease identification system using ECG signal,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 2s, pp. 15–26, https://ijisae.org/index.php/IJISAE/article/view/3555, Oct. 2023.
X. Zhong, G. Liu, X. Dong, C. Li, H. Li, H. Cui, and W. Zhou, “Automatic seizure detection based on Stockwell transform and transformer,” Sensors, vol. 24, no. 1, Art. no. 77, 2024. https://doi.org/10.3390/s24010077
M. S. A. Reshan, S. Amin, M. A. Zeb, A. Sulaiman, H. Alshahrani, and A. Shaikh, “A robust heart disease prediction system using hybrid deep neural networks,” IEEE Access, vol. 11, pp. 121574–121591, 2023. https://doi.org/10.1109/ACCESS.2023.3328909
A. A. Maulani, S. Winarno, J. Zeniarja, R. T. Putri, and A. N. Cahyani, “Comparison of hyperparameter optimization techniques in hybrid CNN-LSTM model for heart disease classification,” SinkrOn, vol. 8, no. 1, pp. 455–465, 2024. https://doi.org/10.33395/sinkron.v9i1.13219
A. Ogunpola, F. Saeed, S. Basurra, A. M. Albarrak, and S. N. Qasem, “Machine learning-based predictive models for detection of cardiovascular diseases,” Diagnostics, vol. 14, no. 2, Art. no. 144, 2024. https://doi.org/10.3390/diagnostics14020144
D. Ueda, T. Matsumoto, S. Ehara, et al., “Artificial intelligence-based model to classify cardiac functions from chest radiographs: A multi-institutional, retrospective model development and validation study,” Lancet Digit. Health, vol. 5, no. 8, pp. e525–e533, 2023. https://doi.org/10.1016/S2589-7500(23)00107-3
L. Abualigah, S. A. Alomari, M. H. Almomani, et al., “Artificial intelligence-driven translational medicine: A machine learning framework for predicting disease outcomes and optimizing patient-centric care,” J. Transl. Med., vol. 23, Art. no. 302, 2025. https://doi.org/10.1186/s12967-025-06308-6
A. M. Hussein, S. A. Alomari, M. H. Almomani, et al., “A smart IoT-cloud framework with Adaptive Deep Learning for real-time epileptic seizure detection,” Circuits Syst. Signal Process., vol. 44, pp. 2113–2144, 2025. https://doi.org/10.1007/s00034-024-02919-4
G. B. Moody and R. G. Mark, “The impact of the MIT-BIH Arrhythmia Database,” IEEE Eng. Med. Biol. Mag., vol. 20, no. 3, pp. 45–50, 2001. https://doi.org/10.1109/51.932724
P. N. Sankar, R. Jayaram, S. I. Sherly, C. Gnanaprakasam, and V. R. R. Raja, “Study of ECG analysis based cardiac disease prediction using deep learning techniques,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 4, pp. 431–438, https://ijisae.org/index.php/IJISAE/article/view/3540, Oct. 2023.
V. Gupta, N. K. Saxena, A. Kanungo, P. Kumar, and S. Diwania "PCA as an effective tool for the detection of R-peaks in an ECG signal processing," International Journal of Systems Assurance Engineering and Management. 2022;13(5):2391–403. https://doi.org/10.1007/s13198-022-01650-0.
Muyideen AbdulRaheem, Idowu Dauda Oladipo, Alfonso González-Briones, Joseph Bamidele Awotunde, Adekola Rasheed Tomori and Rasheed Gbenga Jimoh, "Chapter6: “An efficient lightweight SPECK technique for edge-IoT-based smart healthcare systems,” 5G IoT and Edge Computing for Smart Healthcare, Intelligent Data-Centric Systems., pp 139-162, 2022, https://doi.org/10.1016/B978-0-323-90548-0.00005-X.
Xiaoshan Zhang, Xiaolong Chen, Yinwei Li, Yonggang Luo, and Yiming Zhu, “ECG recognition based on deep convolutional neural network with dual attention mechanism,” Biomed. Signal Process. Control, vol. 113, Art. no. 109142, 2026. https://doi.org/10.1016/j.bspc.2025.109142.
Jinyong Cheng, Qingxu Zou and Yunxiang Zhao, “ECG signal classification based on deep CNN and BiLSTM,” BMC Med. Inform. Decis. Mak., vol. 21, Art. no. 365, 2021. https://doi.org/10.1186/s12911-021-01736-y.
M. Guhdar, A. O. Mohammed and R. J. Mstafa, "Advanced deep learning framework for ECG arrhythmia classification using 1D-CNN with attention mechanism," Knowledge-Based Systems, Vol 315, Art. no. 113301, 2025, doi.org/10.1016/j.knosys.2025.113301.
Jae-Won Choi, Dae-Yong Hong, Chan Jung, Eugene Hwang, Sung-Hyuk Park and Seung-Young Roh, "A Multi-View learning approach to enhance automatic 12-Lead ECG diagnosis performance,” Biomed. Signal Process. Control, vol. 93, Art. no. 106214, 2024. https://doi.org/10.1016/j.bspc.2024.106214.
A. Eleyan, F. Bayram and G. Eleyan, "Spectrogram-Based Arrhythmia Classification Using Three-Channel Deep Learning Model with Feature Fusion," Applied Sciences, 2024; 14(21):9936, doi.org/10.3390/app14219936.
M. S. Tahsin, H. Y. Adarbah and A. Noore, "A Lightweight Channel-Attention CNN for Robust Beat-Level Arrhythmia Detection," in IEEE Access, vol. 14, pp. 62803-62817, 2026, doi: 10.1109/ACCESS.2026.3686810.
Y. Elmir, Y. Himeur and A. Amira, "ECG classification using Deep CNN and Gramian Angular Field," 2023 IEEE Ninth International Conference on Big Data Computing Service and Applications (BigDataService), Athens, Greece, 2023, pp. 137-141, doi: 10.1109/BigDataService58306.2023.00026.
Yangcheng Huang, Wenjing Liu, Ziyi Yin, Shuaicong Hu, Mingjie Wang and Wenjie Cai, "ECG classification based on guided attention mechanism,"Computer Methods and Programs in Biomedicine, Vol 257, 108454, 2024, doi.org/10.1016/j.cmpb.2024.108454.
Sajad Mousavi, Fatemeh Afghah and U. Rajendra Acharya, "HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks," Computers in Biology and Medicine, Vol 127, 104057, 2020, doi.org/10.1016/j.compbiomed.2020.104057.
L. Zheng, M. Zhang, L. Qiu, G. Ma, W. Zhu and L. Wang, "A multi-scale convolutional neural network for heartbeat classification," 2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), Shenyang, China, 2021, pp. 1488-1492, doi: 10.1109/TrustCom53373.2021.00213.
M. Najia and B. Faouzi, "An Enhanced Hybrid Model Combining CNN, BiLSTM, and Attention Mechanism for ECG Segment Classification," Biomed Eng Comput Biol., Vol 16, pp. 1-14, 2025, doi: 10.1177/11795972251341051.
P. N. Malleswari, V.K. Odugu, T. J. V. Subrahmanyeswara Rao, and T. V. N. L. Aswini, “Deep learning-assisted arrhythmia classification using 2-D ECG spectrograms,” EURASIP Journal on Advances in Signal Processing, Vol. 2024, Art. no. 104, 2024. https://doi.org/10.1186/s13634-024-01197-1.
Copyright (c) 2026 Nandakumar P, Kotteeswaran C, Sathya S, Kavitha P, Edwin Raja S, Selvaraj D
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)
