BDBComp
Parceria:
SBC
Algoritmo de Enxame de Partículas Híbrido Aplicado a Clusterização de Dados

Gustavo H. A. SousaAhmed A. A. Esmin

Clusteringisanimportantdataminingtaskandhasbeenexploredex- tensively by a number of researchers for different application areas such as text application and bio-informatics data. The Particle Swarm Optimization (PSO) is a technique based on social behavior that has been successfully applied to several types of problems. In this paper we propose the use of a novel algo- rithm for clustering data that we call Hybrid Particle Swarm Optimization with Mutation (HPSOM) which is based on PSO. The HPSOM basically uses PSO and by incorporating the mutation process often used in Genetic Algorithms to allow the search to escape from local optima. It is shown how the PSO/HPSOM can be used to find the centroids of a user specified number of clusters. The new algorithm is evaluated on real clustering benchmark data. The proposed method is compared with k-means clustering technique and standard Particle Swarm clustering algorithm. The results show that the algorithm is efficient and produces compact clusters.

http://www.lbd.dcc.ufmg.br/colecoes/enia/2011/0039.pdf

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