Título: Multimodal Optimization As A Clustering Task: General Formulation And Application In The Context Of Particle Swarm
Autores: Prampero, Paulo S.; Boccato, Levy; Attux, Romis
Resumo: In this paper, we propose a formulation of the optimization problem as a clustering task, which has the potential of allowing an interchange between approaches belonging to both fields of research and may also allow a straightforward treatment of multimodal scenarios. The proposal is tested using the classical k-means algorithm and a particle swarm algorithm as an accessory tool, and the results indicate the relevance of the clustering-based formulation in terms of search space exploration capability.
Palavras-chave: Clustering-based optimization; multimodal optimization; magnetic particle swarm; k-means algorithm
Código DOI: 10.21528/CBIC2011-10.5
Artigo em pdf: st_10.5.pdf
Arquivo BibTex: st_10.5.bib