摘要
首先从理论上对三种传统遗传算子的作用进行了定量分析,在此基础上提出了一种新的遗传算子——扩散算子,并利用模拟退火法给出了扩散概率.这种增加扩散算子的遗传算法,较好地克服了传统遗传算法易发生成熟前收敛和收敛速度过慢的缺点,仿真结果表明了其实用性和有效性.
In this paper, the actions of three traditional genetic operators are demonstrated through theoretical analysis.
Then one novel genetic operator, the diffusion operator, is presented. And the diffusion probability is given on
the basis of simulated annealing algorithm. The new genetic algorithm with diffusion operator can effectively
solve the problems of premature convergence and slow speed of convergence. The simulation result shows its
utility.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2004年第2期239-243,共5页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金(No.60234010)
南京航空航天大学青年科学基金(No.S9919305)
关键词
模式
扩散算子
扩散式遗传算法
Schema
Diffusion Operator
Diffusion Genetic Algorithm
