BDBComp
Parceria:
SBC
A Clustering Method for Symbolic Interval-Type Data Using Adaptive Chebyshev Distances

Francisco de A. T. de CarvalhoRenata M. C. R. de SouzaFabio C. D. Silva

This work presents a partitioning method for clustering symbolic interval-type data using a dynamic cluster algorithm with adaptive Chebyshev distances. This method furnishes a partition and a prototype for each cluster by optimizing an adequacy criterion that measures the fitting between the clusters and their representatives. To compare interval-type data, the method uses an adaptive Chebyshev distance that changes for each cluster according to its intra-class structure at each iteration of the algorithm. Experiments with real and artificial interval-type data sets demonstrate the usefulness of the proposed method.

http://springerlink.metapress.com/content/wktv438212gk5py3/?p=0c296a4dfa714f4eacbeacd15b1e0b55&p

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD