Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (27): 178-180.

• 数据库与信息处理 • Previous Articles     Next Articles

Algorithm for decision rules reduction based on binary discernibility matrix

WANG Xi-huai,ZHANG Teng-fei,XIAO Jian-mei   

  1. Department of Electrical and Automation,Shanghai Maritime University,Shanghai 200135,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-21 Published:2007-09-21
  • Contact: WANG Xi-huai

基于二进制可辨矩阵的决策规则约简算法

王锡淮,张腾飞,肖健梅   

  1. 上海海事大学 电气自动化系,上海 200135
  • 通讯作者: 王锡淮

Abstract: The decision rules reduction,namely deleting the redundant attribute values of each rule in decision table,is an important topic in the research on data reduction based on rough set theory.It can be achieved by heuristic information after attribute reduction.A method for calculating decision rules core based on binary discernibility matrix is presented directly.And then,an algorithm for decision rules reduction is designed,which is suitable for not only consistent decision table but also inconsistent decision table.

Key words: rough set theory, binary discernibility matrix, attribute reduction, decision rules reduction, decision table

摘要: 决策规则的约简是利用决策逻辑分别消去每一条决策规则中的冗余属性值,是粗糙集理论知识约简的重要内容,一般是在属性约简之后采用启发式信息实现决策规则的约简。基于二进制可辨矩阵给出一个简单的直接求取决策规则核的方法,并提出一种决策规则的约简算法。所给算法简单直观,不但适用于相容决策表,也适用于不相容的决策表。

关键词: 粗糙集, 二进制可辨矩阵, 属性约简, 决策规则约简, 决策表