基于独立成分分析的谱聚类方法

A Spectral Clustering Method Based on ICA

谱聚类是近年来一类具有较好应用前景的聚类方法。本文将独立成分分析引入到传统的谱聚类方法中,提出了一种基于独立成分分析的谱聚类算法。利用独立成分析作为预处理,消除了数据内的冗余信息,使得待聚类数据点在高阶统计量的意义下相互独立。文中对比实验证明了该方法的有效性。

Spectral clustering has attracted many researchers.In this paper,Independent Component Analysis（ICA） is applied to the traditional spectral clustering method.The ICA-based spectral clustering algorithm is proposed.With the ICA algorithm as a preprocess step,the redundancy in sample data is eliminated.The results of the experiments show that the method is effective.