基于粗糙集属性重要性的模糊聚类决策及应用  

Fuzzy clustering decision based on significance of attributes of rough sets and its applications

作　　者：巩增泰[1] 姚红霞[1] 李娟[1] 孙秉珍[1] 

机构地区：[1]西北师范大学数学与信息科学学院,甘肃兰州730070

出　　处：《兰州理工大学学报》2007年第3期135-138,共4页Journal of Lanzhou University of Technology

基　　金：国家自然科学基金(40340235053);甘肃省教育厅科研基金(0601-20)

摘　　要：考虑到不同属性之间的重要性,利用粗糙集理论对模糊信息表或信息表中的不同属性之间(特别是定量属性与定性属性之间)进行耦合,提出一种计算不同属性间相似度的计算方法,即基于粗糙集属性重要性的模糊聚类方法,解决模糊信息表或信息表中属性值定量与定性描述并存情况下的聚类问题,并根据原类结果建立决策表.A new method was proposed for calculating the similarity of different attributes to each other, i. e. , the fuzzy clustering decision based on the significance of attributers by considering the significance of the different attributes and then coupling these attributes allocated in the fuzzy information table or information table （especially the quantitative attributes and the qualitative attributes） with rough sets theory. Thus the problem of clustering the quantitative attributes and the qualitative attributes coexisting in information table as solved and the decision table was set up in accordance with the result of the fuzzy clustering.

关 键 词：粗糙集 模糊聚类 属性重要性 

分 类 号：O211[理学—概率论与数理统计]