Choosing the optimal number of generations in the genetic algorithms with binary-real solutions coding

Authors

  • Александр Евгеньевич Мочалин Kyiv State Maritime Academy named after hetman Petro Konashevich-Sahaydachniy, str. Frunze 9, Kyiv, 04071, Ukraine https://orcid.org/0000-0002-1326-0181

DOI:

https://doi.org/10.15587/2312-8372.2015.51612

Keywords:

genetic algorithm, binary-real coding, stopping criterion, optimization

Abstract

This work is devoted to the problem of choosing the optimal stopping criterion in the transition from the binary coding to the real number coding in genetic algorithms with binary-real representation of solutions in the chromosomes. The main criteria for stopping the modern genetic algorithms based on the phenotype or genotype of individuals are considered. Their advantages and disadvantages are presented.

The main purpose of research is to develop a new intermediate stopping criterion of genetic algorithm with binary-real coding. The developed criteria based on the fact that the values of best chromosomes change within a certain low threshold for some generations. New intermediate stopping criterion allows the efficient spending computing resources using genetic algorithms with binary-real coding.

A comparative efficiency analysis of the new stopping criterion of the transition from one type of coding to another in the optimization of complex multi-extremal function is conducted. Efficiency analysis allowed forming recommendations for the selection of the threshold values in the calculation of a new stopping criterion. The same analysis showed inefficient use of population convergence criterion as an intermediate stopping criterion. The advantages of the new criterion above the criteria based on the fact that the value of the best chromosomes is constantly for several generations are presented.

Author Biography

Александр Евгеньевич Мочалин, Kyiv State Maritime Academy named after hetman Petro Konashevich-Sahaydachniy, str. Frunze 9, Kyiv, 04071

Candidate of Technical Science, Associate Professor

Department of information technology

References

  1. Gill, F., Miurrei, U., Rait, M. (1985). Prakticheskaia optimizatsiia. Translated from English. Moscow: Mir, 509.
  2. Gladkov, L. A., Kureichik, V. V., Kureichik, V. M. (2006). Geneticheskie algoritmy. Moscow: FIZMATLIT, 320.
  3. Whitley, D. (1994, June). A genetic algorithm tutorial. Statistics and Computing, Vol. 4, № 2, 65–85. doi:10.1007/bf00175354
  4. Holland, J. H. (1992). Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. Cambridge: A Bradford Book, 211.
  5. Mochalin, A. (2015). Binary-real coding of solutions in genetic algorithms. Technology Audit And Production Reserves, 3(2(23)), 41–45. doi:10.15587/2312-8372.2015.44992
  6. Le, K. H., Surkova, N. E., Ostrouh, A. V. (2014). Geneticheskie algoritmy v zadachah ratsional'noi organizatsii informatsionno – vychislitel'nyh protsessov. Avtomatizatsiia i upravlenie v tehnicheskih sistemah, 4, 82–99.
  7. Diaz-Gomez, P. A., Hougen, D. F. (2009). Three interconnected parameters for genetic algorithms. Proceedings of the 11th Annual conference on Genetic and evolutionary computation, 763–770. doi:10.1145/1569901.1570007
  8. Tuite, C., Agapitos, A., O'Neill, M., Brabazon, A. (2011). Early Stopping Criteria to Counteract Overfitting in Genetic Programming. Presented at the 13th Annual conference companion on Genetic and evolutionary computation. Dublin, Ireland, 203–204. doi:10.1145/2001858.2001971
  9. Bhandari, D., Murthy, C. A., Pal, S. K. (2012). Variance as a Stopping Criterion for Genetic Algorithms with Elitist Model. Fundamenta Informaticae, 120(2), 145–164. doi:10.3233/FI-2012-754
  10. Bertone, E., Alfonso, H., Gallard, R. (1999).Contrasting termination criteria for genetic algorithms. I Workshop de Investigadores en Ciencias de la Computacion. Argentina, 5.

Downloads

Published

2015-09-22

How to Cite

Мочалин, А. Е. (2015). Choosing the optimal number of generations in the genetic algorithms with binary-real solutions coding. Technology Audit and Production Reserves, 5(2(25), 40–45. https://doi.org/10.15587/2312-8372.2015.51612

Issue

Vol. 5 No. 2(25) (2015): Information technologies. Mathematical modeling

Section

Information Technologies: Original Research

License

Copyright (c) 2016 Александр Евгеньевич Мочалин

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.