Arquitetura híbrida interpretável baseada em wavelet para classificação multiclasse de batimentos de ECG
DOI:
https://doi.org/10.33414/rtyc.56.22-39.2026Palavras-chave:
ECG, classificação de arritmias cardíacas, transformada wavelet, aprendizado profundo, transformador, redes neurais profundasResumo
Apresenta-se uma arquitetura híbrida de aprendizado profundo para a classificação multiclase de batimentos eletrocardiográficos (ECG) utilizando o conjunto de dados MIT-BIH Arrhythmia. A abordagem combina blocos convolucionais multiescala do tipo Inception com convoluções separáveis em profundidade (depthwise separable convolutions), codificadores Transformer unidimensionais (Transformer 1D), unidades recorrentes bidirecionais baseadas em Gated Recurrent Units (BiGRU) e mecanismos de atenção contextual. A representação de cada batimento é enriquecida por meio de características estatísticas obtidas a partir de transformadas wavelet discretas multiescala e por meio de um ramo temporal decimado derivado do sinal original. Para lidar com o desequilíbrio de classes, são empregadas estratégias de aumento fisiológico controlado, Borderline-SMOTE e uma função de perda focal ponderada. O modelo atingiu 99,88% de precisão no treinamento e 98,97% na validação, demonstrando ainda elevada separabilidade no espaço latente e coerência interpretativa por meio da análise SHapley Additive exPlanations (SHAP). Os resultados sugerem que a integração de representações espectro-temporais explícitas com modelagem profunda híbrida constitui uma alternativa robusta, interpretável e computacionalmente eficiente para a classificação automática de arritmias cardíacas.
Downloads
Referências
Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., Adam, M., Gertych, A., Tan, R. S. (2017). A deep convolutional neural network model to classify heartbeats. Computers in Biology and Medicine, 89, 389–396. https://doi.org/10.1016/j.compbiomed.2017.08.022
Addison, P. S. (2005). Wavelet transforms and the ECG: A review. Physiological Measurement, 26(5), R155–R199. https://doi.org/10.1088/0967-3334/26/5/R01
Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition, 1251-1258. https://doi.org/10.1109/CVPR.2017.195
Daubechies, I. (1992). Ten lectures on wavelets. Society for Industrial and Applied Mathematics (SIAM). https://doi.org/10.1137/1.9781611970104
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C. K., & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215-e220. https://doi.org/10.1161/01.CIR.101.23.e215
Han, H., Wang, W. Y., & Mao, B. H. (2005). Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. In: Huang, DS., Zhang, XP., Huang, GB. (eds). Advances in Intelligent Computing. ICIC 2005. Lecture Notes in Computer Science, vol 3644. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11538059_91
He, X., Hu, C., Ma, K., Huang, J., & He, H. (2025). ECG-based arrhythmia classification using discrete wavelet transform and attention-enhanced CNN-BiGRU model. Physical and Engineering Sciences in Medicine, 48, 1995–2009. https://doi.org/10.1007/s13246-025-01639-6
Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-Excitation Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. 7132–7141. https://doi.org/10.1109/CVPR.2018.00745
Huang, G., Sun, Y., Liu, Z., Sedra, D., & Weinberger, K. Q. (2016). Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds). Computer Vision – ECCV 2016. ECCV 2016. Lecture Notes in Computer Science, vol 9908. Springer, Cham. https://doi.org/10.1007/978-3-319-46493-0_39
Islam, M. S., Hasan, K. F., Sultana, S., Uddin, S., Lio’, P., Quinn, J. M. W., & Moni, M. A. (2023). HARDC: A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN. Neural Networks, 162, 271–287. https://doi.org/10.1016/j.neunet.2023.03.004
Ismail Fawaz, H., Lucas, B., Forestier, G., Pelletier, C., Schmidt, D. F., Weber, J., Webb, G. I., Idoumghar, L., Muller, P. A., & Petitjean, F. (2020). InceptionTime: Finding AlexNet for time series classification. Data Mining and Knowledge Discovery, 34(6), 1936–1962. https://doi.org/10.1007/s10618-020-00710-y
Jun, T. J., Nguyen, H. M., Kang, D., Kim, D., Kim, Y.-H., & Kim, D. (2018). ECG arrhythmia classification using a 2-D convolutional neural network. arXiv preprint arXiv:1804.06812.
Kachuee, M., Fazeli, S., & Sarrafzadeh, M. (2018). ECG heartbeat classification: A deep transferable representation. In 2018 IEEE International Conference on Healthcare Informatics (ICHI), 443–444. https://doi.org/10.1109/ICHI.2018.00092
Lin, T. -Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017). Focal loss for dense object detection. 2017 IEEE International Conference on Computer Vision, Venice, Italy. 2980-2988. https://doi.org/10.1109/ICCV.2017.324
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30. https://arxiv.org/abs/1705.07874
Mallat, S. (1989). A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7), 674–693. https://doi.org/10.1109/34.192463
Meng, L., Tan, W., Ma, J., Wang, R., Yin, X., & Zhang, Y. (2022). Enhancing dynamic ECG heartbeat classification with lightweight transformer model. Artificial Intelligence in Medicine, 124, 102236. https://doi.org/10.1016/j.artmed.2022.102236
Pasupa, K., Vatathanavaro, S., & Tungjitnob, S. (2020). Convolutional neural network based focal loss for class imbalance problem: A case study of canine red blood cells morphology classification. arXiv preprint arXiv:2001.03329.
Ramachandran, P., Zoph, B., & Le, Q. V. (2017). Searching for activation functions. arXiv preprint arXiv:1710.05941.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 1–9. https://doi.org/10.1109/CVPR.2015.7298594
van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605. https://www.jmlr.org/papers/v9/vandermaaten08a.html
World Health Organization. (2023). Cardiovascular diseases (CVDs). https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
Yu, S. -N., & Chen, Y. -H. (2007). Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network. Pattern Recognition Letters, 28(10), 1142–1150. https://doi.org/10.1016/j.patrec.2007.01.017
Zhao, Z. (2023). Transforming ECG Diagnosis: An In-depth Review of Transformer-based Deep Learning Models in Cardiovascular Disease Detection. arXiv preprint arXiv:2306.01249.
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2026 Cesar Christian Holote Larrosa, Carlos Marcelo Gomez, Daniel Turra
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial 4.0 International License.
