• DocumentCode
    1560768
  • Title

    A new Multi-parent Recombination Genetic Algorithm

  • Author

    Gong, Daoxiong ; Xiaogang Ruan

  • Author_Institution
    Coll. of Electron. Inf. & Control Eng., Beijing Univ. of Technol., China
  • Volume
    3
  • fYear
    2004
  • Firstpage
    2099
  • Abstract
    This paper proposes a new Multi-parent Recombination Genetic Algorithm, which introduces a new Fitness-Weighted Crossover (FWX) and adopts a random threshold based mechanism to determine the parent-number of multi-parent recombination. FWX is the generalization of Single-point Crossover, Two-point Crossover, Multi-point Crossover, Uniform Crossover, Arithmetic Crossover and Multi-parent Occurrence Based Scanning Crossover. It endures the fitter parent a bigger influencing factor, which is used to determine the contribution of parents to their offspring. The new GA approach guarantees the validity of the offspring by the fact that FWX is a convex combination of parents. Experiment on a suit of benchmark functions validated the advantages of our approach.
  • Keywords
    genetic algorithms; genetics; arithmetic crossover; benchmark functions; fitness weighted crossover; fitter parent; multiparent occurrence based scanning crossover; multiparent recombination genetic algorithm; multipoint crossover; parent number; random threshold based mechanism; single point crossover; two point crossover; uniform crossover; Biological cells; Biological system modeling; Computational biology; Genetic mutations; Organisms;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
  • Print_ISBN
    0-7803-8273-0
  • Type

    conf

  • DOI
    10.1109/WCICA.2004.1341955
  • Filename
    1341955