A bio inspired learning scheme for the fractional order kidney function model with neural networks

Zulqurnain Sabir, Shahid Ahmad Bhat, Hafiz Abdul Wahab, Maria Emí­lia Camargo, Gulmira Abildinova, Zhandos Zulpykhar

2024

Full text Open access: Hybrid Metadata (CSL-JSON)
DOI 10.1016/j.chaos.2024.114562
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The numerical procedures of the fractional order kidney function model (FO-KFM) are presented in this study. These derivatives are implemented to get the precise and accurate solutions of FO-KFM. The nonlinear form of KFM is separated into human (infected, susceptible, recovered) and the components of water (calcium, magnesium). Three cases of FO-KFM are numerically accessible using the stochastic computing scaled conjugate gradient neural networks (SCJGNNs). The statics assortment is performed to solve the FO-KFM, which is used as 78 % for verification and 11 % for both endorsement and training. The precision of SCJGNNs is achieved using the achieved and source outcomes. The reference solutions have been obtained by using the Adam numerical scheme. The competence, rationality, constancy is observed through the SCJGNNs accompanied by the imitations of state transition, regression performances, correlation, and error histograms measures.