摘要
基于遗传算法的搜索策略已经在很多领域得到了成功的应用,该文给出了一个以此为基础的数据挖掘原型系统的解决方案。文中着重讨论了适用于数据挖掘的遗传算子的设计问题,包括如何设计适合于转换为SQL查询语句的编码方式、与数据库良好结合的适应度函数、以及相应的交叉、变异算子等关键问题,还给出了该原型系统的系统组成结构以及主算法框架。
Search strategies based on genetic algorithm have been applied successfully in a wide range of applications.This paper proposes a solution to apply it in data mining works.It focuses on several key points in process of designing genetic -based algorithm suitable for data mining,such as to find an encoding method by which individual can be transformed into a SQL sentence easily,to design a fitness function,a cross-over operator,a mutation operator and so on.It also presents the system framework and main algorithm of the prototype system.
出处
《计算机工程与应用》
CSCD
北大核心
2004年第15期26-27,125,共3页
Computer Engineering and Applications
基金
博士点基金资助(编号:99061116)
重庆市科委攻关项目资助(编号:5990)
