How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis

by: Chris Fraley, Adrian E Raftery

The Computer Journal, Vol. 41, No. 8. (1998), pp. 578-588.

View FullText article

CiteSeer (at Penn State), CiteSeer (at MIT), CiteSeer (at Zurich), CiteSeer (at Singapore)

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

yaroslavvb, arsyed, wnpx, archroad, dgront, ctacmo, KaraNagai, Statistics_and_Social_Science (group), Biostatistics (group), robertlischke

Find related articles with these CiteULike tags

bic, clusteranalysis, cluster_analysis, clustering, dataanalysis, datamining, em_algorithm, mixture_model, model-based, statistics, validation

摘要

We consider the problem of determining the structure of clustered data, without prior knowledge of the number of clusters or any other information about their composition. Data are represented by a mixture model in which each component corresponds to a different cluster. Models with varying geometric properties are obtained through Gaussian components with different parameterizations and cross-cluster constraints. Noise and outliers can be modeled by adding a Poisson process component....

@article{citeulike:543355, abstract = {We consider the problem of determining the structure of clustered data, without prior knowledge of the number of clusters or any other information about their composition. Data are represented by a mixture model in which each component corresponds to a different cluster. Models with varying geometric properties are obtained through Gaussian components with different parameterizations and cross-cluster constraints. Noise and outliers can be modeled by adding a Poisson process component....}, author = {Fraley, Chris and Raftery, Adrian E. }, citeulike-article-id = {543355}, journal = {The Computer Journal}, keywords = {clustering}, number = {8}, pages = {578--588}, posted-at = {2006-04-18 14:26:28}, priority = {2}, title = {How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis}, url = {http://citeseer.ist.psu.edu/fraley98how.html}, volume = {41}, year = {1998} }

RIS record

TY - JOUR ID - citeulike:543355 L3 - citeulike-article-id:543355 N2 - We consider the problem of determining the structure of clustered data, without prior knowledge of the number of clusters or any other information about their composition. Data are represented by a mixture model in which each component corresponds to a different cluster. Models with varying geometric properties are obtained through Gaussian components with different parameterizations and cross-cluster constraints. Noise and outliers can be modeled by adding a Poisson process component.... IS - 8 JF - The Computer Journal EP - 588 TI - How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis VL - 41 SP - 578 KW - clustering AU - Fraley, Chris AU - Raftery, Adrian PY - 1998/// UR - http://citeseer.ist.psu.edu/fraley98how.html ER -

RIS BibTeX