基于核的K-均值聚类

Kernel-based K-means Clustering

将核学习方法的思想应用于K-均值聚类中,提出了一种核K-均值聚类算法,算法的主要思想是:首先将原空间中待聚类的样本经过一个非线性映射,映射到一个高维的核空间中,突出各类样本之间的特征差异,然后在这个核空间中进行K-均值聚类。同时还将一种新的核函数应用于核K-均值聚类中以提高算法的速度。为了验证算法的有效性,分别利用人工和实际数据进行K-均值聚类和核K-均值聚类,实验结果显示对于一些特殊的类分布数据,核K-均值聚类比K-均值聚类具有更好的聚类效果。

The paper applieds the idea of kernel-based learning methods to K-means clustering. It proposes an algorithm of kernel K-means clustering. The idea of the algorithm is firstly map the data from their original space to a high dimensional space (or kernel space) where the data are expected to be more separable then perform K-means clustering in the high dimensional space. Meanwhile it improves the speed of the algorithm by using a new kernel function---conditionally positive definite kernel (CPD). The performance of new algorithm is demonstrated to be superior to that of K-means clustering algorithm by experiments on artificial and real data.