文档介绍:2 2 2
ter ensemble is how to combine multiple clusterers to yield a superior result.
Spectral clustering is brought forth into solving this problem and similarity matrix spectral algorithm ( SMSA) is
proposed. Since the computational cost of SMSA is too high for large document datasets , the charactiristic of spectral
clustering algorithm is further investigated. The hyperedges’similarity matrix are spectral analysed and hyperedges
similarity matrix based meta clustering algorithm ( HSM MCLA) is proposed. Experiments on real world document
sets show that both SMSA and HSM MCLA outperform other cluster ensemble techniques based on graph
partitioning , and HSM MCLA attains comparable results to SMSA with much lower computational cost than SMSA.
Key words : Clustering analysis ; Cluster ensemble ; Spectral clustering ; Document clustering ; Matrix approximation
1 引 言 结果[2 ] . 最常见的方法是 CSPA [ 3 ] ,其中调用图划分
[4 ]
聚类分析是极其困难而又非常重要的问题. 作 算法 M ETIS 对 S 进行聚类. Strehl 和 Gho sh 还提
为无监督学习的主要方法之一 ,其目标是发现对象/