An improved genetic algorithm for solving deceptive problems

Based on the research on deceptive problems of genetic algorithms (GAs), this paper proposes an improved GA to solve deceptive problems. This method, by defining the diversity measure of gene loci for elitist individuals, deduces some gene loci which may cause schema deception. Then, the algorithm performs the complementary operation for these gene loci of elitist individuals. At last, this paper selects the trap function to do some experiments, and the experimental results show that this method is effective to solve deceptive problems of GAs.

[1]  L. Darrell Whitley,et al.  Tracking primary hyperplane competitors during genetic search , 1992, Annals of Mathematics and Artificial Intelligence.

[2]  Abdollah Homaifar,et al.  Analysis and Design of a General GA Deceptive Problem , 1991, International Conference on Genetic Algorithms.

[3]  Jacques Lévy Véhel,et al.  Holder functions and deception of genetic algorithms , 1998, IEEE Trans. Evol. Comput..

[4]  Kalyanmoy Deb,et al.  Sufficient conditions for deceptive and easy binary functions , 1994, Annals of Mathematics and Artificial Intelligence.

[5]  D. E. Goldberg,et al.  Simple Genetic Algorithms and the Minimal, Deceptive Problem , 1987 .

[6]  L. Darrell Whitley,et al.  Deception, dominance and implicit parallelism in genetic search , 1992, Annals of Mathematics and Artificial Intelligence.

[7]  L. Darrell Whitley,et al.  Fundamental Principles of Deception in Genetic Search , 1990, FOGA.

[8]  L. Darrell Whitley,et al.  The Only Challenging Problems Are Deceptive: Global Search by Solving Order-1 Hyperplanes , 1991, ICGA.

[9]  Shengxiang Yang.  Adaptive group mutation for tackling deception in genetic search , 2004 .

[10]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[11]  Gary B. Lamont,et al.  Multi-objective fast messy genetic algorithm solving deception problems , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).