Web客户的核聚类

提出了一种基于核的聚类方法,增加对样本特征的优化;通过核函数,把数据样本空间映射到一个高维的特征空间;在特征空间对数据样本进行k-中心点聚类,并通过计算类内距离作为适应度准则,取其最优的结果。通过Web日志挖掘中的Web客户聚类应用比较,表明核聚类方法在性能上比经典的聚类算法有较大的改进,从而实现更为准确的聚类。

Kernel clustering algorithm for Web clients

A clustering algorithm is proposed for cluster analysis in this paper. We adopt the traditional clustering methods and the kernel technique to construct our kernel clustering algorithm. By using kernel functions, we can map the data in the original space to a high dimension feature space in which we can use the k-medoids clustering algorithm, and we adopt the best by computing the distance. The features of kernel clustering algorithm are accurate in clustering, compared with classical clustering algorithms. Experiments of customers clustering show the effectiveness of the algorithm.