Analysis of the use of activated wavelet functions in wavelet neural networks for categorizing ECG cardiac reductions
Year: 2025
Type: article
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.
Authors: Ігор Думин, Адріан Наконечний
Institution: Lviv Polytechnic National University
Language: English
Topic: ECG Monitoring and Analysis
Subfield: Cardiology and Cardiovascular Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4413517252