相容关系下的分割知识约简算法的研究  

Research on Vertical Segmentation Knowledge Reduction Algorithm Based on Tolerance Rough Set Theory

作　　者：焦娜[1] 

机构地区：[1]华东政法大学信息科学与技术系,上海201620

出　　处：《计算机科学》2016年第1期49-52,共4页Computer Science

基　　金：国家社科基金青年项目(13CFX049);上海高校青年教师培养资助计划(hdzf10008)资助

摘　　要：粗糙集理论是一个能有效地删除冗余特征的工具。由于实际应用的数据往往是连续的,并且结构复杂、特征多,现有的粗糙集知识约简方法对真实复杂的数据计算效率较低。为此,首先将相容关系应用于粗糙集的知识约简,再将复杂的信息表纵向分割成简单的缩减表和小规模信息表,然后把缩减表和小规模信息表连接起来进行知识约简。实例表明,提出的方法能够有效提高粗糙集对复杂数据的计算效率。Rough set theory is an efficient mathematical tool for further reducing redundancy.However,practical data sets are always continuous and the structure is complex.The efficiency of Many existing knowledge reduction methods based on rough set theory are low.This paper combined tolerance relation together with rough set theory.Then,we put forward a new knowledge reduction method based on vertical segmentation.The large information system was divided into one reduced form and other small scale information forms,then they were joined together in order to solve the original information system.An example demonstrates that the proposed algorithm is effective.

关 键 词：粗糙集理论 相容关系 复杂数据 分割 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]