Heuristic computing with active set method for the nonlinear Rabinovich–Fabrikant model

Zulqurnain Sabir, Dumitru Baleanu, Sharifah E Alhazmi, Salem Ben Said

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


The current study shows a reliable stochastic computing heuristic approach for solving the nonlinear Rabinovich-Fabrikant model. This nonlinear model contains three ordinary differential equations. The process of stochastic computing artificial neural networks (ANNs) has been applied along with the competences of global heuristic genetic algorithm (GA) and local search active set (AS) methodologies, i.e., ANNs-GAAS. The construction of merit function is performed through the differential Rabinovich-Fabrikant model. The results obtained through this scheme are simple, reliable, and accurate, which have been calculated to optimize the merit function by using the GAAS method. The comparison of the obtained results through this scheme and the conventional reference solutions strengthens the correctness of the proposed method. Ten numbers of neurons along with the log-sigmoid transfer function in the neural network structure have been used to solve the model. The values of the absolute error are performed around 10−07 and 10−08 for each class of the Rabinovich-Fabrikant model. Moreover, the reliability of the ANNs-GAAS approach is observed by using different statistical approaches for solving the Rabinovich-Fabrikant model.

Original languageEnglish
Article numbere22030
Issue number11
Publication statusPublished - Nov 2023


  • Active set method
  • Artificial neural networks
  • Genetic algorithm
  • Numerical solutions
  • Rabinovich-Fabrikant

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Heuristic computing with active set method for the nonlinear Rabinovich–Fabrikant model'. Together they form a unique fingerprint.

Cite this