Estimating the Parameters of Nonlinear Regression Models Through Particle Swarm Optimization

Ozsoy V. S., ÖRKCÜ H. H.

GAZI UNIVERSITY JOURNAL OF SCIENCE, vol.29, no.1, pp.187-199, 2016 (ESCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 29 Issue: 1
  • Publication Date: 2016
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus
  • Page Numbers: pp.187-199
  • Keywords: Particle swarm optimization, nonlinear regression, parameter estimation, ALGORITHMS
  • Gazi University Affiliated: Yes


Nonlinear regression models are widely used for modeling of stochastic phenomena and the estimating parameters problem plays a central role in the inference in nonlinear regression models. In this paper, this problem has been briefly discussed and an effective approach based on the Particle Swarm Optimization (PSO) algorithm is proposed in order to enhance the estimation accuracy. The PSO algorithm is tested on the well-known 28 nonlinear regression tasks of various level of difficulty. The results show that PSO approach which exhibits a rapid convergence to the minimum value of the sum of squared error function in less iterations, provides accurate estimates and is satisfactory for the parameter estimation of the nonlinear regression models.