首页 | 官方网站   微博 | 高级检索  
     

粗粒度多尺度属性约简启发式算法
引用本文:屈志毅,吴换霞,刘瑜.粗粒度多尺度属性约简启发式算法[J].昆明理工大学学报(理工版),2007,32(4):20-23,38.
作者姓名:屈志毅  吴换霞  刘瑜
作者单位:兰州大学,信息科学与工程学院,兰州,730000
摘    要:粗糙集理论(RS)从它出现到现在一直是数据推理方面的一种强有力的工具,而作为数据推理的一个非常重要组成部分——知识的约简也一直是粗糙集理论的研究重点.本文基于信息论中信息熵、相对熵和条件熵的概念和性质,在粗糙集系统中增加了一个粗粒度逼近量,并根据粗粒度逼近量提出了一种多尺度逼近的属性约简或者叫规则提取的新算法.

关 键 词:粗糙集合    条件熵  相对熵  粗粒度
文章编号:1007-855X(2007)04-0020-04
修稿时间:2006-12-30

A New Algorithm of Elicitation for Attribute Reduction Based on Rough Granulation and Multi-Scale Variable
QU Zhi-yi,WU Huan-xia,LIU Yu.A New Algorithm of Elicitation for Attribute Reduction Based on Rough Granulation and Multi-Scale Variable[J].Journal of Kunming University of Science and Technology(Natural Science Edition),2007,32(4):20-23,38.
Authors:QU Zhi-yi  WU Huan-xia  LIU Yu
Affiliation:School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
Abstract:Rough Set Theory(RS) is a kind of strong tool in the application of data reasoning,and attribute reduction as an important aspect in data reasoning is always a research focus of rough set theory.Based on the characteristics of entropy,relevant entropy and condition entropy,a rough granulation approaching variable is added in the rough set theory.And based on this rough granulation approaching variable,a new multi-scale approaching algorithm is presented,which can also be entitled attribute reduction algorithm.
Keywords:rough set  entropy  condition entropy  relevant entropy  tough granulation
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号