###
DOI:
Journal of Software:1997.8(2):137-144

基于家族优生学的进化算法
吴少岩,张青富,陈火旺
(国防科技大学计算机系,长沙,410073)
A NEW EVOLUTIONARY ALGORITHM BASED ON FAMILY EUGENICS
WU Shaoyan,ZHANG Qingfu,CHEN Huowang
()
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 2634   Download 2924
    Revised:February 15, 1996
> 中文摘要: 模拟进化有几种典型方法,分别强调自然进化过程的不同侧面.人们已意识到恰当地结合这些方法将推进该领域的研究.本文将现有进化方法的差别归结为“遗传链”与“进化链”之间的差别,提出一种新的进化模型,称之为“基于家族优生学的进化FEBE(familyeugenicsbasedevolution)”.新的模型用家族优生学的思想将遗传链与进化链溶为一体,将正交设计技术引入家庭的子代培植以加强个体的行为改进.本文将FEBE模型用于求解困难的Goldberg欺骗问题,取得了满意的实验结果.
Abstract:Several popular approaches of simulated evolution have been developed separately.These approaches emphasize different facets of the natural evolutionary processes,respectively.One has recognized that the simulated evolution will benefit from the adequate combination between the approaches.This paper characterizes the primary difference among existing approaches as the difference between genetic link and behavioral link.A new model of simulated evolution,called FEEE(family eugenics based evolution),is proposed,which combines the genetic link with the behavioral link in light of the idea of family eugenics.In the FEBE model the orthogonal design technique is introduced into offspring’S breeding inside a family SO as to enhance the behavioral improvement of individuals.The FEBE model is applied to solve Goldberg’S deceptive problem that is challenging to most evolutionary algorithms.The exciting experimental results are achieved.
文章编号:     中图分类号:    文献标志码:
基金项目:本文研究得到国家863高科技项目基金,国防科技大学校预研项目资金资助. 本文研究得到国家863高科技项目基金,国防科技大学校预研项目资金资助.
Foundation items:
Reference text:

吴少岩,张青富,陈火旺.基于家族优生学的进化算法.软件学报,1997,8(2):137-144

WU Shaoyan,ZHANG Qingfu,CHEN Huowang.A NEW EVOLUTIONARY ALGORITHM BASED ON FAMILY EUGENICS.Journal of Software,1997,8(2):137-144