作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2010, Vol. 36 ›› Issue (3): 218-220,. doi: 10.3969/j.issn.1000-3428.2010.03.073

• 人工智能及识别技术 • 上一篇    下一篇

基于规则归纳的遗传算法选择和参数设置

李 婷,崔杜武   

  1. (西安理工大学计算机科学与工程学院,西安 710048)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2010-02-05 发布日期:2010-02-05

Genetic Algorithm Selection and Parameter Setting Based on Rule Induction

LI Ting, CUI Du-wu   

  1. (Faculty of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048)
  • Received:1900-01-01 Revised:1900-01-01 Online:2010-02-05 Published:2010-02-05

摘要: 在设计遗传算法时,讨论算法种类的选取和控制参数的设置,基于规则归纳方法,提出一种研究遗传算法种类选择和控制参数设置的实验模型,以遗传算法数值优化问题为背景,用统一结构描述遗传算法实验,利用属性分组等操作规范训练集与决策树算法SLIQ进行规则归纳,将获取的规则用于指导遗传算法设计,并用设计出的算法解决某函数的优化求解问题。

关键词: 遗传算法控制参数, 规则归纳, SLIQ算法

Abstract: In the design of genetic algorithm, the major issues are selection of algorithm type and parameter setting in Genetic Algorithm(GA). Based on rule induction, this paper puts forward a test model that can study the selection of algorithm type and parameter setting in GA. Taking numerical optimization technique using GA as a background, try to give a unified format to describe genetic algorithm experiments, and regulates the training dataset by some methods, for example, fields grouping. The most important part of this test model is rule induction making use of decision tree algorithm SLIQ. Through that process, it can get a set of rules which can guide the design of GA.

Key words: Genetic Algorithm(GA) control parameter, rule induction, SLIQ algorithm

中图分类号: