摘要
邻域粗糙集模型在处理完备的数值型数据中得到广泛应用,但针对不完备的数值型和符号型混合数据进行属性约简的讨论相对较少。为此,首先结合邻域粗糙集给出了可变精度模型下不完备邻域决策系统的上、下近似算子及属性约简;然后通过邻域粒化的方法构建了广义邻域下可变精度的粗糙集模型,并提出了一种属性重要度的评价方法;在此基础上,设计出了面向不完备邻域决策系统的属性约简算法,该算法可直接处理不完备的数值型和符号型混合数据;最后,通过实例分析验证了本文提出的算法能够求解出变精度下不完备邻域决策系统的属性约简结果。
Neighborhood rough set model has been widely used in numerical data processing complete,but the discussion of attribute reduction for numeric and symbolic mixed incomplete data is relatively small. Therefore,to resolve this problem,by combining the neighborhood rough set,first,the upper and lower approximation operators and the attribute reduction of the incomplete neighborhood decision system were analyzed based on the variable precision model. Subsequently,based on the generalized neighborhood relation,a rough set model was constructed using the neighborhood granulation method. Furthermore,a method evaluating the attribute significance degree was proposed. Based on this method,an attribute reduction algorithm for the incomplete neighborhood decision system was designed,which can deal with incomplete values directly type and symbolic mixed data. Finally,through the example analysis,the algorithm can solve the attribute reduction result of incomplete neighborhood decision system with variable precision.
出处
《智能系统学报》
CSCD
北大核心
2017年第3期386-391,共6页
CAAI Transactions on Intelligent Systems
基金
国家自然科学基金项目(61502213
71461013
61462038)
江西省自然科学基金项目(20151BAB217009
20132BAB201045)
江西省教育厅科学技术项目(GJJ150399
GJJ150505)
关键词
粗糙集理论
邻域关系
不完备信息系统
变精度分类粗糙集
粒计算
多粒度
约简
决策粗糙集
rough set theory
neighborhood relation
incomplete information system
variable precision classification
granular computing
multi-granulation
reducation
decision-theoretic rough sets
