基于粒子群的不完备决策表属性约简PSOIDTAR法  

PSOIDTAR method based on particle swarm optimization for attribution under incomplete decision-making table

作　　者：曾正良[1] 罗可[1] 王莹[2] 

机构地区：[1]长沙理工大学计算机与通信工程学院,长沙410076 [2]湖南师范大学数学与计算机科学学院,长沙410081

出　　处：《计算机工程与应用》2008年第14期149-151,204,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.10471036,No.60474070);湖南省科技厅科研项目基金(No.05FJ3074);湖南省教育厅重点项目(No.07A001)

摘　　要：属性约简是粗糙集理论的一个核心部分。由于经典的粗糙集模型对不完备信息系统不适应,通过把属性约简问题归结为0-1组合优化问题,提出了一种应用二进制粒子群算法来求解属性约简的方法。通过引入近似分类精度和近似分类质量,为获得最小约简确定了有效合理的粒子适应度函数。仿真实验结果表明该算法能得到最小相对约简,且具有较高的运算效率。Attribution reduction is the core of the rough set theory. Because the theory of the classical rough set can＇ t apply to the incomplete decision-making table, the paper proposes a rough set attribute reduction algorithm based on the binary Particle Swarm Optimization （ PSO）, taking the attribution reduction to a part of the 0-1 combination optimization problem. The paper imports approximate classified precision and the approximate classified quality, and makes an efficient particle adaptive function in order to get a best reduction. Finally,experimental results show the algorithm can find the minimal relative reduction,and it is fast and effective.

关 键 词：粗糙集 不完备决策表 粒子群算法 属性约简 PSOIDTAR 

分 类 号：TP311.131[自动化与计算机技术—计算机软件与理论]