东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2004, Vol. 25 ›› Issue (6): 551-554.DOI: -

• 论著 • 上一篇    下一篇

一种基于概括约简的特征提取新方法

张德干;尹国成;郝先臣;赵海   

  1. 东北大学信息科学与工程学院;东北大学信息科学与工程学院;东北大学信息科学与工程学院;东北大学信息科学与工程学院 辽宁沈阳　110004
  • 收稿日期:2013-06-24 修回日期:2013-06-24 出版日期:2004-06-15 发布日期:2013-06-24
  • 通讯作者: Zhang, D.-G.
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(69873007)

New character-abstraction method based on generalization and reduction

Zhang, De-Gan (1); Yin, Guo-Cheng (1); Hao, Xian-Chen (1); Zhao, Hai (1)   

  1. (1) Sch. of Info. Sci. and Eng., Northeastern Univ., Shenyang 110004, China
  • Received:2013-06-24 Revised:2013-06-24 Online:2004-06-15 Published:2013-06-24
  • Contact: Zhang, D.-G.
  • About author:-
  • Supported by:
    -

RichHTML

1

PDF (PC)

644

摘要： 为适应特征级信息融合计算的需要,在粗糙集理论框架下,提出了一种基于概括约简的特征提取新方法·首先引入层次树的概念研究了属性值的抽象概括方法,然后设计了两种带有互补性的属性约简方法,一种是利用条件属性间的相关性作为约简策略去除冗余条件属性,另一种是利用有效一致性因子原则约简无关条件属性·设计的方法弥补了粗糙集理论中目前还存在的处理对象范围狭窄和处理效果较差等方面缺陷·应用实例验证了方法的正确性和可信性·

关键词: 特征提取, 融合计算, 粗糙集, 概括约简, 层次树, 相关性, 一致性

Abstract: To meet the requirements of information fusion computing at character-level, a character-abstraction method based on generalization and reduction is presented based on the rough set theory. The method of generalizing the values of attribute is studied according to the concept of level tree. Then, based on the principles of minimum average relativity and maximum consistency factor, two kinds of reduction methods are designed owning to their special goals, i.e., reducing redundancy attributes and reducing relative mapping relationship. The designed method can overcome the existing shortcomings of narrow object range and bad effect of the methods within the rough set theory. The correctness and dependability of the method are verified by application example.

中图分类号: