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
Link To Document :
بازگشت