EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Bayesian Regularized Dual Hidden‐Layer RBF Neural Network Approach for SEIR‐Based Computer Network Epidemics

Zulqurnain Sabir, Ghalia Nassreddine

Complexity · 2026-01 · 2026 (1)

DOI: 10.1155/cplx/3930272 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complexity, online erschienen am 19.11.2026. Verfasst von Zulqurnain Sabir und 1 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study provides an accurate and reliable framework for a neural network to solve the computer‐network epidemic model of six compartments. The proposed method is based on a dual hidden‐layer neural network structure using radial basis functions, with 15 and 32 neurons in Hidden Layers 1 and 2, while Bayesian regularization is used in training. The Euler numerical scheme is used for generating reference solutions with a step size of 0.01, which is divided into training and testing subsets. The performance of the scheme is assessed based on mean squared error, state‐transition analysis, error histograms, fitness performance, regression analysis, absolute‐error analysis, and comparisons between the proposed and the reference solutions. The training MSE reaches around 5.690 × 10 −13 with respect to the Euler reference data, which themselves differ from a high‐accuracy solution by up to about 8 × 10 −4 . The execution time varies slightly from case to case (around 11 to 20 s). Therefore, the results indicate that the Bayesian‐regularized dual hidden‐layer neural network reproduces the reference dynamics of the computer‐network model under various initial conditions with stable training and low computational cost.

Zitieren

APA

Sabir, Z., & Nassreddine, G. (2026). A Bayesian Regularized Dual Hidden‐Layer RBF Neural Network Approach for SEIR‐Based Computer Network Epidemics. Complexity, 2026(1). https://doi.org/10.1155/cplx/3930272

Vancouver

Sabir Z, Nassreddine G. A Bayesian Regularized Dual Hidden‐Layer RBF Neural Network Approach for SEIR‐Based Computer Network Epidemics. Complexity. 2026;2026(1). doi:10.1155/cplx/3930272

BibTeX
@article{Sabir2026,
  author = {Sabir, Zulqurnain and Nassreddine, Ghalia},
  title = {A Bayesian Regularized Dual Hidden‐Layer RBF Neural Network Approach for SEIR‐Based Computer Network Epidemics},
  journal = {Complexity},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/cplx/3930272}
}
Kostenlos starten →