International Journal of Computational Intelligence Systems (Aug 2016)

A hybrid gene expression programming algorithm based on orthogonal design

  • Jie Yang,
  • Jun Ma

DOI
https://doi.org/10.1080/18756891.2016.1204124
Journal volume & issue
Vol. 9, no. 4

Abstract

Read online

The last decade has witnessed a great interest on the application of evolutionary algorithms, such as genetic algorithm (GA), particle swarm optimization (PSO) and gene expression programming (GEP), for optimization problems. This paper presents a hybrid algorithm by combining the GEP algorithm and the orthogonal design method. A multiple-parent crossover operator is introduced for the chromosome reproduction using the orthogonal design method. In addition, an evolutionary stable strategy is also employed to maintain the population diversity during the evolution. The efficiency of the proposed algorithm is evaluated using three benchmark problems. The results demonstrate that the proposed hybrid algorithm has a better generalization ability compared to conventional algorithms.

Keywords