摘要
为了改善K-means算法的聚类效果,将聚类准则函数定义为加权的类内误差平方总和SSE(sum of thesquared error),并调整了K-means算法迭代过程中重新分配数据对象的方法:使用一个带有类内数据对象数的加权距离作为重新分配数据对象的依据,同时按类间差异最大化为准则优化了加权距离中的参数。实验表明,改进后的K-means算法可以在很大程度上减少大类被拆分情况的发生,明显改善聚类效果。
To find natural clusters,the criterion function was improved by being defined as the weighted sum of the squared error.The way each point assigned to the centroid in the iteration of the K-means algorithm was also modified： each point was assigned to the centroid that had minimum weighted distance.The weight was related to the number of points in each cluster,and the parameter of weighted distance was optimized by maximizing the between-cluster variation.Experimental results showed that the improved K-means algorithm significantly enhanced the clustering quality by reducing the probability of larger cluster＇s being broken.
出处
《山东大学学报（理学版）》
CAS
CSCD
北大核心
2010年第7期28-33,共6页
Journal of Shandong University(Natural Science)
基金
上海财经大学‘211工程’三期重点学科建设项目
关键词
K-MEANS算法
聚类
类间差异
加权距离
K-means algorithm
clustering
between-cluster variation
weighted distance
