Refereed full papers (journals, book chapters, international conferences)

2004

@article{LFJ2004,
	vgclass =	{refpap},
	author =	{Martin H. C. Law and Mario A. T. Figueiredo and Anil K. Jain},
	title =	{Simultaneous Feature Selection and Clustering Using
	Mixture Models},
	journal =	{IEEE Transactions on Pattern Analysis and Machine Intelligence},
	volume =	{26},
	number =	{9},
	pages =	{1154-01166},
	month =	{September},
	year =	{2004},
	url =	{http://dx.doi.org/10.1109/TPAMI.2004.71},
	abstract =	{Clustering is a common unsupervised learning technique
	used to discover group structure in a set of data. While there exist
	many algorithms for clustering, the important issue of feature
	selection, that is, what attributes of the data should be used by the
	clustering algorithms, is rarely touched upon. Feature selection for
	clustering is difficult because, unlike in supervised learning, there
	are no class labels for the data and, thus, no obvious criteria to
	guide the search. Another important problem in clustering is the
	determination of the number of clusters, which clearly impacts and is
	influenced by the feature selection issue. In this paper, we propose
	the concept of feature saliency and introduce an
	expectation-maximization (EM) algorithm to estimate it, in the context
	of mixture-based clustering. Due to the introduction of a minimum
	message length model selection criterion, the saliency of irrelevant
	features is driven toward zero, which corresponds to performing feature
	selection. The criterion and algorithm are then extended to
	simultaneously estimate the feature saliencies and the number of
	clusters.},
}