基于改进遗传算法的关联挖掘方法研究  

Association Mining Method Based on Improved Genetic Algorithm

作　　者：郑玉柱[1] 李建[1] 李珂[1] 

机构地区：[1]西南石油大学计算机科学学院,成都610500

出　　处：《重庆科技学院学报（自然科学版）》2015年第5期72-76,共5页Journal of Chongqing University of Science and Technology：Natural Sciences Edition

基　　金：国家科技重大专项"钻井工程设计和工艺软件"(2011ZX05021-006)

摘　　要：数值型关联规则挖掘是最优化问题而不是简单的离散问题,在大型数据库中挖掘数值型属性的关联规则具有一定的难度。为解决该问题,提出一种基于改进遗传算法的数据挖掘方法。针对数值型属性和布尔型属性的混合数据,设计一种分类并分界的编码方法;适应度函数采取范围收缩的策略,使属性边界向更精确的方向逼近;在此基础上设计出相应的交叉和变异算法,避免遗传算法的局部收敛和早熟问题;最后通过实例检验该算法的可行性。In this paper a genetic- based association rule mining algorithm is proposed to deal with the problem of mining quantitative association rule in large database,because it is an optimization problem rather than a simple discretization one. First,we designed an encoding method for classification and division based on the blended data from boolean and quantitative attributes. Then the attributes＇ amplitudes are shortened by the search strategy of fitness function when the boundary is droven more accurate. It is designed to avoid the local convergence and premature problems with appropriate crossover and mutate methods. Finally,the efficiency of the algorithm is validated by the test upon real database.

关 键 词：数据挖掘 关联规则 数值型属性 遗传算法 适应度函数 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]