Tuning maturity model of ecogeography-based optimization on CEC 2015 single-objective optimization test problems

Ecogeography-based optimization (EBO) is an extension of biogeography-based optimization (BBO) that evolves a population of solutions by continually migrating features among them, mimicking the principle of immigration and emigration of species from one habitat to another in biogeographical distribution. The original EBO uses a linear maturity model for balancing exploration and exploitation. In this paper we generalize the maturity model by introducing a single control parameter, and then tune the parameter for each test problem of the CEC 2015 learning-based benchmark problem suite in order to find the most effective model for solving the problem. We design a binary search method for conveniently and effectively tuning the model. The computational experiments show that the tuned algorithm can improve the solution quality on different problems of the benchmark suite significantly.