Scholarlink

<p>The purpose of the current investigation is to design a novel radial basis neural network for solving the dynamical hepatitis C virus model in patients with a high baseline viral load, which represents the nonlinear dynamical structure. The infection and treatment in the hepatitis C virus comprise uninfected hepatocytes, creatively infected hepatocytes, and viruses. The aim of this study is to solve the dynamical hepatitis C virus model in patients with a high baseline viral load with the optimization of the Bayesian regularization scheme. A database reference solution is achieved by the explicit Runge–Kutta in interval 0 and 1 with the step size of 0.01 by data division into training as 72%, while 14%, 14% for endorsement, and testing. Twenty numbers of neurons, a feed forward neural network, activation radial basis function, and the optimization Bayesian regularization approach have been used to solve the hepatitis C virus model. The precision of the scheme is perceived by the outcomes overlapping and the reducible absolute error values, which are found as 10<sup>–06</sup> to 10<sup>–08</sup>. A statistical evaluation utilizing various operators and proportional approaches is carried out in order to assess the solver’s efficiency.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Designing a novel radial basis neural structure for solving the dynamical hepatitis C virus model

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月21日

查看全文
  • Zulqurnain Sabir,
  • Adilkazy Yessengaliyev,
  • Abdikhalyk Temirzhan,
  • Hikmet Koyunbakan,
  • Saira Bhatti,
  • Rana Nicolas

摘要

The purpose of the current investigation is to design a novel radial basis neural network for solving the dynamical hepatitis C virus model in patients with a high baseline viral load, which represents the nonlinear dynamical structure. The infection and treatment in the hepatitis C virus comprise uninfected hepatocytes, creatively infected hepatocytes, and viruses. The aim of this study is to solve the dynamical hepatitis C virus model in patients with a high baseline viral load with the optimization of the Bayesian regularization scheme. A database reference solution is achieved by the explicit Runge–Kutta in interval 0 and 1 with the step size of 0.01 by data division into training as 72%, while 14%, 14% for endorsement, and testing. Twenty numbers of neurons, a feed forward neural network, activation radial basis function, and the optimization Bayesian regularization approach have been used to solve the hepatitis C virus model. The precision of the scheme is perceived by the outcomes overlapping and the reducible absolute error values, which are found as 10–06 to 10–08. A statistical evaluation utilizing various operators and proportional approaches is carried out in order to assess the solver’s efficiency.