基于粗糙集理论的区间型多属性灰决策规则及应用  

Grey Decision Rules for Interval Multiple Attributes Decision Analysis and Application Based on Rough Sets

作　　者：解铭[1] 

机构地区：[1]邯郸学院,河北邯郸056005

出　　处：《模糊系统与数学》2016年第3期105-113,共9页Fuzzy Systems and Mathematics

基　　金：邯郸市科学技术研究与发展计划项目(1438201080-2);河北省高等学校科学技术研究项目(QN2014309

摘　　要：本文在粗糙集理论的基础上,针对属性值为区间数的信息系统,提出了一种新的决策规则。首先,借助于改进的粗糙聚类算法对区间型属性值进行离散化,之后通过构造划分同族矩阵来确定属性约简集。最后,基于灰色关联分析技术提出了灰色决策规则。而在属性权重的确定方面,通过属性相对重要性的定义构造互反矩阵,利用遗传算法解优化模型得到属性权重。Based on rough sets, a new decision rule for information system with interval numbers is proposed. First of all, the interval number values are discretized through improved rough clustering algorithm.Then the reductant set of attributes is obtained by constituting homogenous matrix.Finally, we propose grey decision rules based on grey relational analysis. As far as the weights of attribute were concerned, the reciprocal matrix is constituted by the definition of relative significance between two attributes and then the optimal model which expresses the reciprocal matrix is solved by genetic algorithm.

关 键 词：粗糙聚类 区间数 灰色关联分析 BP神经网络 

分 类 号：O29[理学—应用数学]