Numerical Investigations through ANNs for Solving COVID-19 Model

The current investigations of the COVID-19 spreading model are presented through the artificial neuron networks (ANNs) with training of the Levenberg-Marquardt backpropagation (LMB), i.e., ANNs-LMB. The ANNs-LMB scheme is used in different variations of the sample data for training, validation, and...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Muhammad Umar, Zulqurnain Sabir, Muhammad Asif Zahoor Raja, Shumaila Javeed, Hijaz Ahmad, Sayed K. Elagen, Ahmed Khames
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
R
Acceso en línea:https://doaj.org/article/23c1381115464cf180fb87e547c8c2c7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:The current investigations of the COVID-19 spreading model are presented through the artificial neuron networks (ANNs) with training of the Levenberg-Marquardt backpropagation (LMB), i.e., ANNs-LMB. The ANNs-LMB scheme is used in different variations of the sample data for training, validation, and testing with 80%, 10%, and 10%, respectively. The approximate numerical solutions of the COVID-19 spreading model have been calculated using the ANNs-LMB and compared viably using the reference dataset based on the Runge-Kutta scheme. The obtained performance of the solution dynamics of the COVID-19 spreading model are presented based on the ANNs-LMB to minimize the values of fitness on mean square error (M.S.E), along with error histograms, regression, and correlation analysis.