Abstract
Genetic algorithms (GAs) are stochastic optimization techniques, and the theoretical study of the process of GA evolution is very important in the application of GA. Mutation is one of most important operators in GA, and Markov chain theory has attracted researchers’ attention for the study of mutation. By applying Markov chain to study symmetric mutation model in GA, we have obtained the relation between the mutation rate and the evolution of the first order schema. This paper theoretically analyzes the effects of mutation rates on GA with asymmetric mutation, and studies the evolution and stationary distribution of the first order schema. This study focuses on effects of asymmetry to the linkage of loci, and shows the degree of asymmetry in mutation has a large effect on the evolution of the first order schema.
Similar content being viewed by others
References
Levin DA, Peres Y, Wilmer EL (2008) Markov Chains and Mixing Times. American Mathematical Society, Providence
Du Y, Ma Q, Furutani H (2015) Hitting time analysis of OneMax problem in genetic algorithm. J Robot, Netw Artif Life 2(2):131–134
Lobry JR, Sueoka N (2002) Asymmetric directional mutation pressures in bacteria. Genome Biology 3:58.1–58.14
Wada K, Doi H, Tanaka S (1993) A neo-Darwinian algorithm: Asymmetrical mutation due to semiconservative DNA-type replication promote evolution. Proceedings of National Academy of Science, USA 90, pp 11934–11938
Nei M (2013) Mutation-driven evolution. Oxford University Press, Oxford
Furutani H, Sakamoto M, Du Y (2015) Analysis of asymmetric mutation model in random local search. J Robot Netw Artif Life 2(1):1–4
Jansen T, Sudholt D (2010) Analysis of an asymmetric mutation operator. Evol Comput 18(1):1–26
Doerr B, Hebbinghaus N, Neumann F (2007) Speeding Up Evolutionary Algorithms through Asymmetric Mutation Operators. Evol Comput 15(4):401–410
Ewens JWJ (2004) Mathematical population genetics. Theoretical introduction, 2nd edn. Springer-Verlag, New York
Furutani H (2004) Effect of linkage disequilibrium in selection—schema analysis of OneMax problem (in Japanese). Trans Math Model Appl 45 No. SIG 2(TOM 10):12–21
Furutani H (2004) Walsh Analysis of Crossover in Genetic Algorithms (in Japanese). Inform Process Soc Jpn 42(9):2270–2283
Ma Q, Zhang Y, Yamamori K (2013) Stochastic analysis of OneMax problem by using Markov chain. Artif Life Robot 17:395–399
Iosifescu M (1980) Finite markov processes and their applications. Wiley, New York
Du Y, Ma Q, Furutani H (2014) Runtime analysis of OneMax problem in genetic algorithm. J Robot Network Artif Life 1(3):225–230
Furutani H, Zhang Y, Sakamoto M (2009) Study of the distribution of optimum solution in genetic algorithm by Markov Chains (in Japanese). Transac Math Model Appl 2(3):54–63
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Du, Y., Aoki, K., Sakamoto, M. et al. Asymmetric mutation model in genetic algorithm. Artif Life Robotics 22, 17–23 (2017). https://doi.org/10.1007/s10015-016-0329-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-016-0329-y