Chapter

Advances in Artificial Intelligence – SBIA 2004

Volume 3171 of the series Lecture Notes in Computer Science pp 385-394

Detecting Promising Areas by Evolutionary Clustering Search

  • Alexandre C. M. OliveiraAffiliated withDepartamento de Informática, Universidade Federal do Maranhão – UFMAInstituto Nacional de Pesquisas Espaciais – INPE, Laboratório Associado de Computação e Matemática Aplicada
  • , Luiz A. N. LorenaAffiliated withInstituto Nacional de Pesquisas Espaciais – INPE, Laboratório Associado de Computação e Matemática Aplicada

* Final gross prices may vary according to local VAT.

Get Access

Abstract

A challenge in hybrid evolutionary algorithms is to define efficient strategies to cover all search space, applying local search only in actually promising search areas. This paper proposes a way of detecting promising search areas based on clustering. In this approach, an iterative clustering works simultaneously to an evolutionary algorithm accounting the activity (selections or updatings) in search areas and identifying which of them deserves a special interest. The search strategy becomes more aggressive in such detected areas by applying local search. A first application to unconstrained numerical optimization is developed, showing the competitiveness of the method.

Keywords

Hybrid evolutionary algorithms unconstrained numerical optimization