Título: Self-Adaptive Differential Evolution Based on the Concept of Population Diversity Applied to Simultaneous Estimation of Anisotropic Scattering Phase Function, Albedo and Optical Thickness.
Revista: Computer Modeling in Engineering and Sciences, 1, 1-17, 2010.
Resumo: Differential Evolution Algorithm (DE) has shown to be a powerful evolutionary algorithm for global optimization in a variety of real world problems. DE differs from other evolutionary algorithms in the mutation and recombination phases. Unlike some other meta-heuristic techniques such as genetic algorithms and evolutionary strategies, where perturbation occurs in accordance with a random quantity, DE uses weighted differences between solution vectors to perturb the population. Although the efficiency of DE algorithm has been proven in the literature, studies indicate that the efficiency of the DE methods is sensitive to its control parameters (perturbation rate and crossover rate) and there is not any guarantee that premature convergence will be avoided. To overcome this problem, the present work proposes an Self-Adaptive Differential Evolution (SADE) as based on the concept of population diversity aiming at dynamically updating the control parameters. The methodology proposed is applied to the simultaneous estimation of the radiation phase function of anisotropic scattering, albedo and optical thickness in an inverse radiative transfer problem. The results show that the procedure represents a promising alternative for the type of problem presented above.

Acessar a Publicação.
Voltar para a seção Revistas.