<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Water resources in Nusa Tenggara Timur have great concentrations based on magnesium and calcium ions thus being referred to as “hard water”. Prolonged hard water consumption has become a reason of kidney disfunction that can cause additional illnesses, like cerebrovascular pathologies and diabetes. Hence, it is crucial to comprehend how drinking hard water affects renal functions. The current study shows the kidney dysfunction model based on hard water consumption by applying the stochastic procedures of the Levenberg-Marquardt backpropagation neural networks (LMBNNs). The kidney dysfunction model of hard water consumption depends upon human components and water. Human dynamics is further divided into susceptible, infected and recovered, while water components are categorized into calcium and magnesium concentration. The log-sigmoid transfer function along with 20 hidden neurons is used to present the solutions of the model. Three cases of the model have been numerically stimulated and the correctness of the stochastic technique is perceived by using the comparison of proposed and reference Adam databased solutions along with the negligible absolute error. Training, validation and testing performances have been applied to reduce the values of the mean square error. Moreover, the statistical performances using the transition of state, error histograms and regression/correlation have been validated to authenticate the reliability of the scheme.</p>
</abstract>

Water resources in Nusa Tenggara Timur have great concentrations based on magnesium and calcium ions thus being referred to as “hard water”. Prolonged hard water consumption has become a reason of kidney disfunction that can cause additional illnesses, like cerebrovascular pathologies and diabetes. Hence, it is crucial to comprehend how drinking hard water affects renal functions. The current study shows the kidney dysfunction model based on hard water consumption by applying the stochastic procedures of the Levenberg-Marquardt backpropagation neural networks (LMBNNs). The kidney dysfunction model of hard water consumption depends upon human components and water. Human dynamics is further divided into susceptible, infected and recovered, while water components are categorized into calcium and magnesium concentration. The log-sigmoid transfer function along with 20 hidden neurons is used to present the solutions of the model. Three cases of the model have been numerically stimulated and the correctness of the stochastic technique is perceived by using the comparison of proposed and reference Adam databased solutions along with the negligible absolute error. Training, validation and testing performances have been applied to reduce the values of the mean square error. Moreover, the statistical performances using the transition of state, error histograms and regression/correlation have been validated to authenticate the reliability of the scheme.

Levenberg-Marquardt backpropagation neural network procedures for the consumption of hard water-based kidney function

Department of Computer Science and Mathematics

International Journal of Mathematics and Computer in Engineering

This work is licensed under the Creative Commons Attribution 4.0 International License.

Water resources in Nusa Tenggara Timur have great concentrations based on magnesium and calcium ions thus being referred to as “hard water”. Prolonged hard...

Levenberg-Marquardt backpropagation neural network procedures for the consumption of hard water-based kidney function

Publié en ligne: 20 juil. 2023

Pages: 127 - 138

Reçu: 23 mai 2023

Accepté: 01 juil. 2023

DOI: https://doi.org/10.2478/ijmce-2023-0010

Mots clés
Kidney, nonlinear model, Levenberg-Marquardt, transfer function, neural networks

© 2023 Zulqurnain Sabir et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Levenberg-Marquardt backpropagation neural network procedures for the consumption of hard water-based kidney function

Publié en ligne: 20 juil. 2023

Pages: 127 - 138

Reçu: 23 mai 2023

Accepté: 01 juil. 2023

DOI: https://doi.org/10.2478/ijmce-2023-0010

Mots clésKidney, nonlinear model, Levenberg-Marquardt, transfer function, neural networks

© 2023 Zulqurnain Sabir et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Kidney, nonlinear model, Levenberg-Marquardt, transfer function, neural networks