期刊文献+

一种新的交叉操作算子 被引量:19

A New Crossover Operator
下载PDF
导出
摘要 论文提出了一种新的遗传操作算子-随机多父辈适应度值加权交叉算子(RandomParent-numberFitness-WeightedCrossover,RPFWX)。RPFWX在2到群体规模之间随机决定参与交叉操作的父代数量,以克服遗传算法的性能对于多父辈数量的敏感性。RPFWX根据父代个体的适应度值赋予较优秀的父代个体以较大的影响因子。父代个体根据该影响因子来决定其对于子代个体贡献的大小。RPFWX是包括两父辈算术交叉、uniformcrossover以及多父辈频率扫描交叉算子(theOccurrenceBasedScanningCrossover)等在内的多种交叉算子的概括和推广,并通过其凸空间封闭特性来保证子代个体的合法性。最后通过实验结果验证了RPFWX算子的优越性。 A new crossover operator named Random Parent-number Fitness-Weighted Crossover(RPFWX)is introduced and studied in this paper.RPFWX randomly choose the parent number in the range from2to the population size since the performance of GA with Multi-Parent Recombination is sensitive to the parent number.RPFWX endues the fitter parent with a bigger influencing factor,and parents decide their contribution to offspring according to the factors.RPFWX is the generalization of the Arithmetical Crossover,Uniform Crossover,the Multi-parent Occurrence Based Scan-ning Crossover,and etc.RPFWX can guarantee the validity of offspring because it is a convex combination of all par-ents.Experiment result validates the advantages of RPFWX.
出处 《计算机工程与应用》 CSCD 北大核心 2004年第6期7-10,46,共5页 Computer Engineering and Applications
基金 国家自然科学基金重点项目资助(编号:60234020)
关键词 遗传算法 多父辈交叉 交叉算子 Genetic algorithm,Multi-parent recombination,Crossover operator
  • 相关文献

参考文献13

  • 1[1]Zbigniew Michalewicz. Genetic Algorithms+Data Structures=Evolution Programs[M].Berlin: Springer-Verlag, 1996
  • 2[2]Goldberg D E.Genetic Algorithm in search,Optimization,and Machine learning[M].Massachusetts: Addison-Wesley, Reading, 1989
  • 3[3]Eshelman L J,Caruana R A,Schaffer J D.Biases in the Crossover Landscape[C].In:Schaffer,J D Eds. Proceedings of the 3rd International Conference on Genetic Algorithms,CA:Morgan Kaufmann Publishers,San Mateo, 1989:10~19
  • 4[4]Syswerda G.Uniform Crossover in Genetic Algorithms[C].In:Schaffer J D Eds. Proceedings of the 3rd International Conference on Genetic Algorithms. CA:Morgan Kaufmann Publishers,San Mateo, 1989:2~9
  • 5[5]Spears W M, De Jong K A.On the Virtues of Parametrized Uniform Crossover[C].In:Belew R, Booker LEds. Proceedings of the 4th International Conference on Genetic Algorithms,CA:Morgan Kaufmann Publishers,San Mateo, 1991:230~236
  • 6[6]Muhlenbein H,Voigt H-M.Gene Pool Recombination for the Breeder Genetic Algorithm[C].In:Proceedings of the Metaheuristics International Conference.Colorado:Breckenridge, 1995:19~25
  • 7[7]K M van Kemenade,A E Eiben.Multi-parent recombination to overcome premature convergence in genetic algorithms[C].In:J C Bioch,Y-H Tan eds. Proceedings of the 7th Dutch Conference on Artificial Intelligence,Erasmus University Press, 1995:137~146
  • 8[8]Eiben A E ,Raue P-E,Ruttkay. Genetic Algorithms with Multi-parent Recombination[C].In :Proceedings of the Parallel Problem Solving from Nature III,1994:78~87
  • 9[9]Eiben A E,van Kemenade C H M,Kok J N.Orgy in the Computer:Multi-Parent Reproduction in Genetic Algorithms[C].In:Proceedings of the 3rd European Conference on Artificial Life,LNAI 929 , SpringerVerlag, 1995: 934~945
  • 10[10]Eiben A E,Schippers,C A.Multi-Parent's Niche:n-ary Crossover on NK-Landscapes[C].In:Proceedings of the Parallel Problem Solving from Nature IV, 1996:319~328

同被引文献109

引证文献19

二级引证文献87

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部