Optimization of Convolutional Neural Networks Using Genetic Algorithms for the Classification of Arrhythmias in Skeletonized ECG Images
Computation · 01.05.2026 · 14 (5) · 104
DOI: 10.3390/computation14050104 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computation, online erschienen am 01.05.2026. Verfasst von Álvaro Gabriel Vega-De la Garza und 6 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Secretaría de Educación, Ciencia, Tecnología e Innovación (SECIHTI) of Mexico.
Abstract (Originalsprache)
Class imbalance among arrhythmia types and electrocardiogram (ECG) signal complexity present significant challenges for automated ECG-based arrhythmia detection. This research proposes an innovative approach that combines Genetic Algorithm (GA) optimization of Convolutional Neural Network (CNN) hyperparameters with morphological skeletonization of ECG images. The MIT-BIH Arrhythmia Database served as the primary data source, with the ECG signal converted to skeletonized representations emphasizing QRS complex geometry. A GA-optimized model was compared against a heuristic (manual design) baseline to determine optimal kernel and filter configurations. Evaluation emphasized not only overall accuracy but also robust metrics for minority classes. The optimized model achieved 97.26% accuracy, with macro recall improving substantially from 77.36% to 83.10% (+5.74%). These results demonstrate that evolutionary optimization enhances detection sensitivity to subtle geometric patterns, effectively mitigating class imbalance without artificial oversampling techniques.
Förderung
- Secretaría de Educación, Ciencia, Tecnología e Innovación (SECIHTI) of Mexico
Zitieren
APA
Garza, Á. G. V. L., Alvarez-Sánchez, E. J., Zaballa-Contreras, J. F., Aldana-Franco, R., Aldana-Franco, F., Leyva-Retureta, J. G., & López-Velázquez, A. (2026). Optimization of Convolutional Neural Networks Using Genetic Algorithms for the Classification of Arrhythmias in Skeletonized ECG Images. Computation, 14(5), 104. https://doi.org/10.3390/computation14050104
Vancouver
Garza ÁGVL, Alvarez-Sánchez EJ, Zaballa-Contreras JF, Aldana-Franco R, Aldana-Franco F, Leyva-Retureta JG, et al. Optimization of Convolutional Neural Networks Using Genetic Algorithms for the Classification of Arrhythmias in Skeletonized ECG Images. Computation. 2026;14(5):104. doi:10.3390/computation14050104
BibTeX
@article{Garza2026,
author = {Garza, Álvaro Gabriel Vega-De la and Alvarez-Sánchez, Ervin Jesús and Zaballa-Contreras, Julio Fernando and Aldana-Franco, Rosario and Aldana-Franco, Fernando and Leyva-Retureta, José Gustavo and López-Velázquez, Andrés},
title = {Optimization of Convolutional Neural Networks Using Genetic Algorithms for the Classification of Arrhythmias in Skeletonized ECG Images},
journal = {Computation},
year = {2026},
volume = {14},
number = {5},
pages = {104},
doi = {10.3390/computation14050104}
}
EUVIMED