基于广义差别矩阵的核和属性约简算法  

Algorithms based on general discernibility matrix for computation of a core and attribute reduction

作　　者：杨明[1] 杨萍[1] 

机构地区：[1]南京师范大学数学与计算机科学学院,南京210097

出　　处：《控制与决策》2008年第9期1049-1054,共6页Control and Decision

基　　金：国家自然科学基金项目(40771163);江苏省自然科学基金项目(BK2005135);江苏省高校自然科学研究基金项目(05KJB5200665)

摘　　要：属性约简是粗糙集理论的重要研究内容.为此引入广义差别矩阵,提出基于广义差别矩阵的核和属性约简算法.该框架可有效避免连续属性值离散化,且有利于与其他机器学习方法相结合.理论分析表明,所提出的算法是有效而可行的.Attributes reduction is one of important parts researched in rough set theory. Therefore, in this paper, after proposing a concept of general discernibility matrix, both computation of a core and attribute reduction algorithms based on general discernibility matrix are introduced. The newly proposed framework can effectively avoid discretizing the eontinuous-valued attributes and be easily incorporated into other machine learning methods. Theoretical analysis sbows the effectiveness of the algorithm.

关 键 词：粗糙集 广义差别矩阵 核 属性约简 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]