核聚类算法

Kernel Clustering Algorithm

该文提出了一种用于聚类分析的核聚类方法 .通过利用 Mercer核 ,作者把输入空间的样本映射到高维特征空间后 ,在特征空间中进行聚类 .由于经过了核函数的映射 ,使原来没有显现的特征突现出来 ,从而能够更好地聚类 .该核聚类方法在性能上比经典的聚类算法有较大的改进 ,具有更快的收敛速度以及更为准确的聚类 .

A new clustering algorithm is proposed for cluster analysis. In general, the reliability of the traditional clustering algorithms strictly depends on the feature difference of data. If the feature differences are large, it is easy to implement clustering. But if the feature differences are small and even cross in the origin space, it is difficult for traditional algorithms to clustering correctly. Authors adopt the traditional clustering methods and the kernel technique to construct own kernel clustering algorithm. By using Mercer kernel functions, the data in the original space can be mapped to a high-dimensional feature space in which clustering can be performed efficiently. The features of kernel clustering algorithm are fast in convergence speed and accurate in clustering, compared with classical clustering algorithms. The results of simulation experiments demonstrate the feasibility and effectiveness of the kernel clustering algorithm.