基于模糊关系传递闭包的聚类方法

Clustering Method Based on Transitive Closure of Fuzzy Relation

  • 摘要: 根据数据之间的相似关系,构造了基于模糊相似关系传递闭包的聚类方法.该方法用数据之间的距离定义模糊相似关系,利用模糊关系的合成算子,构造该关系的传递闭包,该传递闭包是等价关系.以等价类为聚类.实验结果表明该聚类方法可得到与传统K-均值方法相同的聚类结果.

     

    Abstract: Clustering method based on transitive closure of fuzzy relation is formed according to the similarity between data.The proposed method defined the fuzzy similarity by using the distance between data.The transitive closure,which is equivalence relation,is formed by using relation compound operator.The clusters are equivalent classes.The experiments show that the proposed method can achieve the same results as the conventional K-means clustering method.

     

/

返回文章
返回