一种改进的粗糙集理论分层递阶约简算法  

An Improved Hierarchical Reduction Algorithm Based on Rough Set Theory

作　　者：柴慧芳[1] 刘文奇[1] 

机构地区：[1]昆明理工大学理学院,云南昆明650093

出　　处：《昆明理工大学学报（理工版）》2008年第3期104-106,共3页Journal of Kunming University of Science and Technology(Natural Science Edition)

摘　　要：粗糙集的分层递阶约简算法是根据属性的获取方式、采集成本和实时性要求等对属性进行分类,使决策系统中的所有属性在单层次和单粒度上的知识表示变为部分属性所构成的知识在多种层次和多种粒度上的表示,从而可以逐层对决策系统进行约简.在此基础上,文章根据规则获取者的需要即属性的重要度考虑进行分层递阶简约.文章的最后将该算法应用于某单位人才引进决策的获取中,证实了其有效性.The hierarchical reduction approach of rough set theory is elaborated in this paper. In the algorithm, the attributes are firstly partitioned into different parts allocated at several layers. The knowledge in the information systems or decision systems is therefore presented hierarchically with multiple granularities at multiple layers, and the reduction is hierarchically applied to parts of attributes allocated at each layer. An improved hierar- chical reduction algorithm based on the significance of attributes is then proposed. Finally, the developed hierar-chical reduction algorithm is used to acquire the control decision of talents introduction, which verifies the effectiveness of the algorithm.

关 键 词：粗糙集理论 信息系统 决策系统 分层递阶约简 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]