关键词: 全局K-Means, 谱聚类, 初始值敏感

Abstract: Spectral clustering is an effectively widely used clustering method. With the essence of initialization sensitivity in spectral clustering, the Global K-means clustering algorithm was introduced to overcome the disadvantage. Then a spectral clustering algorithm based on global k-means was coming. Compared with the traditional spectral algorithm, some experiments showed that the proposed algorithm was not only effective and feasible but also good at getting stable clustering results and suitably improving clustering precision .

Key words: global K-Means, spectral clustering, initialization sensitivity