改进的Vague等价聚类分析  

Equal cluster analysis for Warshall algorithm at Vague sets

作　　者：张阿红[1] 王治和[1] 孙亮[1] 吴鹏[1,2] 

机构地区：[1]西北师范大学数学与信息科学学院,兰州730070 [2]浙江林学院信息工程学院,浙江临安311300

出　　处：《计算机工程与应用》2008年第35期132-134,共3页Computer Engineering and Applications

基　　金：国家自然科学基金No.10671158;甘肃省教育厅科研基金(No.0701-16);西北师范大学2006~2010年度重点学科“网格计算”~~

摘　　要：Vague关系作为模糊关系的一种推广,在某些情况下,比直觉模糊关系具有更强的模糊信息表达能力。通过对照关系和模糊关系的传递闭包,把求模糊矩阵的传递闭包算法完整地推广到Vague关系矩阵上,从而可以将相似Vague关系矩阵转换为等价Vague关系矩阵,进而通过设定肯定、否定双维度阀值αt、αf,将此等价的Vague关系矩阵转化成一个等价的布尔矩阵,最终使得达到聚类分析的目的。最后通过一个实例给出了这种聚类分析方法在模式识别中的应用。Vague relation as a generalized fuzzy relation has more powerful ability to process fuzzy information thanintuitionistic fuzzy relation in some situations.The Warshall＇s algorithm for transitive closure of relation matrices to that of Vague relation matrices is extended.With the Warshall＇s algorithm,a similarity vague relation matrix is obtained by beginning with a proximity vague relation matrix.Then through the set of negation and affirmation double-dimensionsvalve αt ,αf,equivalent Vague relation matrix is changed into an equivalent of Boolean matrix,to make the ultimate purpose of the cluster analysis,the final adoption is an example of this kind of cluster analysis methods in the application of pattern recognition.

关 键 词：VAGUE集 WARSHALL算法 等价关系 聚类分析 传递闭包 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]