1. RCIPL
2. Comunidades & Colecções
3. ESCS - Escola Superior de Comunicação Social
4. ESCS - Artigos

Título:	Feature selection for clustering categorical data with an embedded modelling approach
Autor:	Silvestre, Cláudia Cardoso, Margarida Figueiredo, Mário
Palavras-chave:	Cluster analysis Finite mixture models EM-MML algorithm Feature selection Categorical features
Data:	23-Set-2014
Editora:	John Wiley & Sons, Ltd
Citação:	Silvestre C., Cardoso M. G. M. S. and Figueiredo M. (2014), Feature selection for clustering categorical data with an embedded modelling approach, Expert Systems
Resumo:	Research on the problem of feature selection for clustering continues to develop. This is a challenging task, mainly due to the absence of class labels to guide the search for relevant features. Categorical feature selection for clustering has rarely been addressed in the literature, with most of the proposed approaches having focused on numerical data. In this work, we propose an approach to simultaneously cluster categorical data and select a subset of relevant features. Our approach is based on a modification of a finite mixture model (of multinomial distributions), where a set of latent variables indicate the relevance of each feature. To estimate the model parameters, we implement a variant of the expectation-maximization algorithm that simultaneously selects the subset of relevant features, using a minimum message length criterion. The proposed approach compares favourably with two baseline methods: a filter based on an entropy measure and a wrapper based on mutual information. The results obtained on synthetic data illustrate the ability of the proposed expectation-maximization method to recover ground truth. An application to real data, referred to official statistics, shows its usefulness.
Peer review:	yes
URI:	http://hdl.handle.net/10400.21/4046
DOI:	10.1111/exsy.12082
Versão do Editor:	http://onlinelibrary.wiley.com/doi/10.1111/exsy.12082/pdf
Aparece nas colecções:	ESCS - Artigos

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.