不完备多尺度决策信息系统的局部泛化约简  

Generalization Reducts in Incomplete Multi-scale Decision Tables

作　　者：贺晓丽[1,2] 刘华丽 钱婷[1,2] HE Xiao-li;LIU Hua-li;QIAN Ting(College of Science,Xi'an Shiyou University,Xi'an 710065,China;Institute of Concepts,Cognition and Intelligence,Northwest University,Xi'an 710027,China)

机构地区：[1]西安石油大学理学院,陕西西安710065 [2]西北大学概念认知与智能研究中心,陕西西安710127

出　　处：《模糊系统与数学》2022年第6期79-88,共10页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(12001422,61976244,12171388);陕西省自然科学基础研究计划项目(2021JQ-580,2020JQ-762);浙江省海洋大数据挖掘与应用重点实验室开放课题(OBDMA202105)。

摘　　要：在不完备多尺度决策信息系统中,研究面向单个对象的局部泛化约简方法。所提的局部泛化约简方法融合了不同特征的不同尺度上的信息,且保持了广义决策值的一致性。在协调的不完备多尺度决策信息系统中,证明了两种泛化约简方法的一致性,给出了相应的的局部泛化约简算法。在不协调多尺度决策信息系统中,研究了其详细性质,并通过实例说明两种泛化约简的区别。In incomplete multi-scale decision tables, a type of local generalization reduct method is investigated. The proposed approach integrates the information of different attributes at diffirent scales, and keeps the generalized decision unchanged. In consistent incomplete multi-scale decision tables, two types of generalization reduct methods are shown to be equivalent, and an algorithm of searching for generalization reducts is designed. In inconsistent multi-scale decision tables, the properties are examined in detail and an example is employed to show the differences between two types of generalization reducts.

关 键 词：不完备信息系统 多尺度不完备信息系统 粒度树 剪枝 局部泛化约简 

分 类 号：O159[理学—数学]