Numerical investigations of the nonlinear smoke model using the Gudermannian neural networks

Math Biosci Eng. 2022 Jan;19(1):351-370. doi: 10.3934/mbe.2022018. Epub 2021 Nov 15.

Abstract

These investigations are to find the numerical solutions of the nonlinear smoke model to exploit a stochastic framework called gudermannian neural works (GNNs) along with the optimization procedures of global/local search terminologies based genetic algorithm (GA) and interior-point algorithm (IPA), i.e., GNNs-GA-IPA. The nonlinear smoke system depends upon four groups, temporary smokers, potential smokers, permanent smokers and smokers. In order to solve the model, the design of fitness function is presented based on the differential system and the initial conditions of the nonlinear smoke system. To check the correctness of the GNNs-GA-IPA, the obtained results are compared with the Runge-Kutta method. The plots of the weight vectors, absolute error and comparison of the results are provided for each group of the nonlinear smoke model. Furthermore, statistical performances are provided using the single and multiple trial to authenticate the stability and reliability of the GNNs-GA-IPA for solving the nonlinear smoke system.

Keywords: Gudermannain neural networks; Runge-Kutta; active-set algorithm; genetic algorithms; nonlinear smoke model; numerical results.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Neural Networks, Computer*
  • Nonlinear Dynamics
  • Reproducibility of Results
  • Smoking*