A Modified Estimation of Distribution Algorithm for Numeric Optimization

Abstract

Estimation of distribution algorithms (EDAs) is a class of probabilistic model-building evolutionary algorithms, which is characterized by learning and sampling the probability distribution of the selected individuals. This paper proposes a modified estimation of distribution algorithm (mEDA) for numeric optimization. mEDA uses a novel sampling method, called centro-individual sampling, and a fuzzy c-means clustering technique to improve its performance. Extensive experiments conducted on a set of benchmark functions show that mEDA outperforms HPBILc, CEGDA, CEGNABGe and NichingEDA, reported in the literature, in terms of the quality of solutions.