计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (14): 115-117.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于分形维数的非常规决策表的属性约简

朱颢东1,张明慧2,李红婵1   

  1. 1.郑州轻工业学院 计算机与通信工程学院,郑州 450002
    2.郑州师范学院 信息技术系,郑州 450044

  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-05-11 发布日期:2011-05-11

Attribute reduction on abnormal decision table based on fractal dimension

ZHU Haodong1,ZHANG Minghui2,LI Hongchan1   

  1. 1.School of Computer and Communication Engineering,Zhengzhou University of Light Industry,Zhengzhou 450002,China
    2.Department of Information Technology,Zhengzhou Normal University,Zhengzhou 450044,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-05-11 Published:2011-05-11

摘要: 属性约简是粗糙集的一个核心研究课题,但经典属性约简及其延伸算法是基于有决策属性的决策表的属性约简算法,它们对无决策属性的非常规决策表的属性约简无能为力。以粗糙集理论为基础,对无决策属性的非常规决策表从分形维数方面进行研究,提出了一种适用于无决策属性的决策表的启发式属性约简算法。该算法在一定程度上能够解决非常规决策表的属性约简问题,进一步扩展了粗糙集理论的应用范围。实例表明该算法是有效可行的。

关键词: 属性约简, 决策属性, 决策表, 分形维数

Abstract: Attribute reduction is a core research topic of rough set,but classical attribute reduction algorithm and its extended algorithms are based on decision tables with decision attributes and can not be applied to attribute reduction of abnormal decision tables without decision attributes.Based on rough set theory,the abnormal decision tables in fractal dimension is studied and a heuristic attribute reduction algorithm is presented.To a certain extent,the algorithm can resolve the attribute reduction problem of abnormal decision tables and extend application of rough set theory.The example shows that the algorithm is effective and feasible.

Key words: attribute reduction, decision attribute, decision table, fractal dimension