论文信息 - CLUSTERING VIA NORMAL MIXTURE MODELSG

CLUSTERING VIA NORMAL MIXTURE MODELSG

We consider a model-based approach to clustering, whereby each observation is assumed to have arisen from an underlying mixture of a nite number of distributions. The number of components in this mixture model corresponds to the number of clusters to be imposed on the data. A common assumption is to take the component distributions to be multivariate normal with perhaps some restrictions on the component covari-ance matrices. The model can be tted to the data using maximum likelihood implemented via the EM algorithm. There is a number of computational issues associated with the tting, including the speciication of initial starting points for the EM algorithm and the carrying out of tests for the number of components in the nal version of the model. We shall discuss some of these problems and describe an algorithm that attempts to handle them automatically.

P. | D. Peel | PradoG

[1] Geoffrey J. McLachlan,et al. On a Resampling Approach to Choosing the Number of Components in Normal Mixture Models , 2007 .

[2] Adrian E. Raftery,et al. Inference in model-based cluster analysis , 1997, Stat. Comput..

[3] G. Celeux,et al. Regularized Gaussian Discriminant Analysis through Eigenvalue Decomposition , 1996 .

[4] G. Celeux,et al. An entropy criterion for assessing the number of clusters in a mixture model , 1996 .

[5] Regularized Gaussian Discriminant Analysisthrough Eigenvalue DecompositionHalima BensmailUniversit , 1996 .

[6] Gérard Govaert,et al. Gaussian parsimonious clustering models , 1995, Pattern Recognit..

[7] S. Klinke,et al. Exploratory Projection Pursuit , 1995 .

[8] Bernhard W. Flury,et al. Error rates in quadratic discrimination with constraints on the covariance matrices , 1994 .

[9] A. Raftery,et al. Model-based Gaussian and non-Gaussian clustering , 1993 .

[10] Geoffrey J. McLachlan,et al. Mixture models : inference and applications to clustering , 1989 .

[11] G. McLachlan. On Bootstrapping the Likelihood Ratio Test Statistic for the Number of Components in a Normal Mixture , 1987 .

[12] Susan R. Wilson. Sound and Exploratory Data Analysis , 1982 .

[13] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[14] R. Fisher. THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .