期刊信息

  • 刊名: 河北师范大学学报(自然科学版)Journal of Hebei Normal University (Natural Science)
  • 主办: 河北师范大学
  • ISSN: 1000-5854
  • CN: 13-1061/N
  • 中国科技核心期刊
  • 中国期刊方阵入选期刊
  • 中国高校优秀科技期刊
  • 华北优秀期刊
  • 河北省优秀科技期刊

一种新的求属性约简的算法

  • 1. 石家庄铁道学院数理系, 河北石家庄050043;
    2. 中国科学院空间科学与应用研究中心, 北京100080
  • DOI:

A New Algorithm for Attribute Reduction

摘要/Abstract

摘要:

以不一致度为基础,给出了一种新的衡量属性重要度的标准—不一致度增加函数,并以此为启发式信息构造了一种新的属性约简算法.与前人提出的属性约简算法相比,这种算法的求核运算包含在求属性重要度的运算中,不需要再单独求核,从而简化了算法,提高了效率.

Abstract:

Based on the degree of inconsistency,a new standard to scale the importance of an at tribute in a decision tablethe deg ree of inconsistency increasing function is proposed.Furthermore,a new algorithm for att ribute reduction is designed.Compared with the others, this algorithm includes the computing of core in the computing of the degree of the att ributes.In this way,this algorithm does not need to calculate the core solely,and thus its time complexity is reduced.