Realization of rational genetic algorithm

Xingjian Jing, Yue Chao Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

By using the feedback of genetic information and heuristic rules, and incorporating local searching algorithms, rational genetic algorithm (RGA) is proposed to overcome the drawbacks of conventional genetic algorithms (GAs) such as slow convergence. Genetic Information was defined, which is the feed-back information derived from evolutionary process to supervise GA's operations. Furthermore, heuristic rules and local searching algorithms were also effectively incorporated in RGA to enhance the correctness of genetic operations. Finally, a general specification for the whole RGA was provided. RGA effectively incorporates inheriting and learning behaviors of knowledge and experiences in species into conventional GA. From the theoretical analysis of RGA and case studies in practical application to path planning problems of robots, it can be seen that the proposed RGA has faster convergence speed, and can converge to the global optimal solution.
Original languageEnglish
Title of host publicationProceedings of the 9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005
Pages11-16
Number of pages6
Publication statusPublished - 1 Dec 2005
Externally publishedYes
Event9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005 - Benidorm, Spain
Duration: 12 Sep 200514 Sep 2005

Conference

Conference9th IASTED International Conference on Artificial Intelligence and Soft Computing, ASC 2005
Country/TerritorySpain
CityBenidorm
Period12/09/0514/09/05

Keywords

  • Convergence
  • Genetic algorithm
  • Genetic information
  • Rational genetic algorithm

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this