首页 | 本学科首页   官方微博 | 高级检索  
     

基于熵测度的自适应遗传算法
引用本文:马强,陈江川,徐晓艳,杨新武,赵琦,邵亚斌.基于熵测度的自适应遗传算法[J].西华大学学报(自然科学版),2013(3):45-49,84.
作者姓名:马强  陈江川  徐晓艳  杨新武  赵琦  邵亚斌
作者单位:西北民族大学网络与信息管理中心;甘肃省城乡规划设计研究院;多媒体与智能软件技术北京市重点实验室,北京工业大学计算机学院;西北民族大学数学与计算机学院
基金项目:国家自然科学基金(11161041);中央高校中青年科研基金项目(ZYJ2012004);西北民族大学中青年科研基金项目(X2009-012)
摘    要:针对基本遗传算法SGA在搜索过程中易陷入局部最优解的问题,提出了基于熵测度的自适应遗传算法,并分析了熵测度下种群个体被选概率的极限行为。理论分析和对比实验表明,基于熵测度的自适应选择策略能根据种群性状来动态地调整选择压力,从而调整算法的开采和探索能力的平衡,提高算法的全局优化性能。

关 键 词:遗传算法  自适应    未成熟收敛

Adaptive Genetic Algorithm Based On Entropy Measurement
MA Qiang,CHEN Jiang-chuan,XU Xiao-yan,YANG Xin-wu,ZHAO Qi,SHAO Ya-bin.Adaptive Genetic Algorithm Based On Entropy Measurement[J].Journal of Xihua University:Natural Science Edition,2013(3):45-49,84.
Authors:MA Qiang  CHEN Jiang-chuan  XU Xiao-yan  YANG Xin-wu  ZHAO Qi  SHAO Ya-bin
Affiliation:1.Northwest University for Nationalities Network Information Management Center,Lanzhou 730030 China;2.GAN SU Institute of Urban Planning and Design,Lanzhou 730000 China;3.Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory,the College of Computer Science,Beijing University of Technology,Beijing 100022 China;4.School of Mathematics and Computer Science Northwest University for Nationalities Lanzhou 730030 China)
Abstract:The basic operation methods and correlative parameters of genetic algorithm indicate the balance between the exploitation and exploration, but the simple genetic algorithm SGA easily gets into local optimal solution in the process of searching. The authors propose an adaptive genetic algorithm based on entropy measurement, and deduce the limit of the selection probabilities of individuals under entropy measurement. The theoretical analysis and a comparative experiment show that the new selection strategy based on entropy measurement can adjust dynamically the selection intensity according to the population state, which improves the global optimal performance of the algorithm.
Keywords:genetic algorithm  self-adaptive  entropy  premature convergence
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号