基于朴素基因表达式编程的函数自动建模
Function Automatic Modeling Based on Naǐve Gene Expression Programming
作者:朱明放(四川大学 计算机学院,四川 成都 610065);唐常杰(四川大学 计算机学院,四川 成都 610065);陈瑜(四川大学 计算机学院,四川 成都 610065)
Author:(School of Computer Sci., Sichuan Univ., Chengdu 610065,China);(School of Computer Sci., Sichuan Univ., Chengdu 610065,China);(School of Computer Sci., Sichuan Univ., Chengdu 610065,China)
收稿日期:2007-09-05 年卷(期)页码:2008,40(4):126-131
期刊名称:工程科学与技术
Journal Name:Advanced Engineering Sciences
关键字:基因表达式编程;二叉树数据结构;自动建模;原子基因串
Key words:Gene Expression Programming(GEP);data structure of binary tree;automatic modeling;atomic gene fragments
基金项目:国家自然科学基金资助项目(60473071);国家科技支撑计划资助项目(2006038002003)
中文摘要
为了进一步提高GEP的函数自动建模的效率,提出了朴素基因表达式编程模型(Naǐve GEP)NGEP;提出了原子基因片断的概念,以保护进化良好的基因片段;引入了基因嫁接操作,实现了NGEP原型。实验表明:NGEP在函数自动建模的收敛速度是标准GEP的2~4倍。
英文摘要
In order to improve the efficiency of GEP in function finding,a novel concept named Naǐve Gene Expression Programming(NGEP) and the concept of atomic gene fragments to preserve good genes were proposed.Gene transplant was introduced and the prototype of NGEP system was implemented. Extensive experiments showed that the convergence speed of NGEP is as 2-4 times as that in the standard GEP.
【关闭】