Parameter estimation of S-shaped growth model: A modified particle swarm algorithm

Abstract

Parameter estimation plays a critical role for the application and development of S-shaped growth model in the agricultural sciences and others. In this paper, a modified particle swarm optimization algorithm based on the diffusion phenomenon (DPPSO) was employed to estimate the parameters for this model. Under the sense of least squares, the parameter estimation problem of S-shaped growth model, taking the Gompertz and Logistic models for example, is transformed into a multi-dimensional function optimization problem. The results show that the DPPSO algorithm can effectively estimate the parameters of the S-shaped growth model.