杂合灰色聚类与变精度粗糙模糊集的概率决策方法

在基于粗糙集理论或扩展粗糙集理论的不确定性管理决策中,仅由数据集无法获得决策表,同时决策属性呈现模糊性,以至于无法获取概率决策规则。鉴于此,本文构建了灰色定权聚类与粗糙集变精度的杂合模型,首先运用基于中心点三角白化权函数的灰色定权聚类方法对包含不同量纲指标的知识表示系统进行处理,生成多属性决策表,而后运用变精度粗糙模糊集进行决策分析,获取概率决策规则。最后以区域关键技术选择为例,表明该模型的可行性与实用性。

Probabilistic Decision Method Based on the Hybrid Model of Grey Clustering and Variable Precision Rough Fuzzy Set

In many uncertain practical decisions based on rough set models or extensions of rough set model,it is impossible to generate decision tables from data set,meanwhile decision attributes possess fuzziness,so that probabilistic decision rules can’t be obtained.A hybrid approach to grey clustering and variable precision rough fuzzy set is proposed in the paper.The basic idea of the hybrid method is as follows.To begin with,a multiple attribute decision table is established by grey fixed weight clustering based on the center triangle whitening weight function,and then probabilistic decision rules from multicriteria decision table are derived by applying variable precision rough fuzzy set.Finally,the proposed method is applied to the selection of regional key technology,and the results show that the method can be feasibility and practicality.