Analysis of the use of activated wavelet functions in wavelet neural networks for categorizing ECG cardiac reductions
Abstract
Accurate and automated classification of heartbeats in an electrocardiogram (ECG) is fundamental to the diagnosis and treatment of cardiovascular diseases (CVD), but it remains a challenging task due to the complexity and variability of ECG signals [1]. This study examines the effectiveness of using various wavelet functions, including Morlet, Mexican Hat, Gabor, Shannon, and Gaussian, as activation functions in a wavelet neural network (WNN) architecture for ECG heart rate classification [3]. Using a publicly available dataset obtained from the MIT-BIH Arrhythmia and PTB Diagnostic ECG databases focusing on the 5-grade arrhythmia categorization based on the Association for the Advancement of Medical Instrumentation (AAMI) standard [5]. The key findings point to differences in the performance of different wavelet activation functions, emphasizing the potential benefits of using the inherent properties of time-frequency localization of wavelets to capture discriminative morphological features in ECG rhythms [7]. This work emphasizes the prospects of using wavelet-based activation functions to improve the accuracy and reliability of deep learning models in biomedical signal processing programs, including ECG analysis.
References
Sörnmo, L., & Laguna, P. (2005). Bioelectrical Signal Processing in Cardiac and Neurological Applications. Academic Press. https://doi.org/10.1016/B978-012437552-9/50003-9
Zhang, Q., & Benveniste, A. (1992). Wavelet networks. IEEE Transactions on Neural Networks, 3(6), 889-898. https://doi.org/10.1109/72.165591
Saragadam, V., Hoffmann, M., & Heckel, R. (2023). WIRE: Wavelet Implicit Neural Representations. arXiv preprint arXiv:2301.05187. https://doi.org/10.1109/CVPR52729.2023.01775
Moody, G.B., & Mark, R.G. (2001). The impact of the MIT-BIH Arrhythmia Database. IEEE Engineering in Medicine and Biology Magazine, 20(3), 45-50. https://doi.org/10.1109/51.932724
Association for the Advancement of Medical Instrumentation. (2008). ANSI/AAMI EC57:1998 (R)2008, Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms. Arlington, VA: AAMI.
de Chazal, P., O'Dwyer, M., & Reilly, R.B. (2004). Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Transactions on Biomedical Engineering, 51(7), 1196-1206. https://doi.org/10.1109/TBME.2004.827359
Mallat, S. (2008). A Wavelet Tour of Signal Processing (3rd ed.). Academic Press.
Hannun, A.Y., Rajpurkar, P., Haghpanahi, M., Tison, G.H., Bourn, C., Turakhia, M.P., & Ng, A.Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory ECGs using a deep neural network. Nature Medicine, 25(1), 65-69. https://doi.org/10.1038/s41591-018-0268-3
Parvaneh, S., Rubin, J., Babaeizadeh, S., & Xu-Wilson, M. (2019). Analyzing the performance of different wavelet families for ECG denoising using neural networks. Sensors (Basel), 19(4), 824.
Fathony, R., Willomitzer, F., Kolter, J.Z., & Raskar, R. (2021). Multiplicative Filter Networks. In International Conference on Learning Representations (ICLR).
Copyright (c) 2025 Ігор Думин, Адріан Наконечний (Автор)
This work is licensed under a Creative Commons Attribution 4.0 International License.
