关键词: 聚类集成，混合型数据，相似性度量

Abstract: A clustering algorithm based on ensemble and spectral technique named CBEST that works well for data with mixed numeric and categorical features was presented. A similarity measure based on clustering ensemble was adopted to define the similarity between pairs of objects,which makes no assumptions of the underlying distributions of the fcature values. A spectral clustering algorithm was employed on the similarity matrix to extract a partition of the data. The performance of CREST was studied on artificial and real data sets. Results demonstrate the effectiveness of this algorithm in clustering mixed data tasks and its robustness to noise. Comparisons with other related clustering schemes illustrate the superior performance of this approach. Moreover, CREST can infuse prior knowledge effectively to set the weights of different features in clustering.

Key words: Clustering ensemble, Mixed data, Similarity measure