Multiobjective optimization using compromise programming and an immune algorithm

Felipe Campelo*, Frederico G. Guimarães, Hajime Igarashi

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

9 Citations (Scopus)

Abstract

The m-AINet is a modified version of the artificial immune network algorithm for single-objective and multimodal optimization (opt-AINet), with constraint-handling capability and improvements aiming to reduce the computational effort required by the original algorithm. In this paper we extend this algorithm for multiobjective problems by using the compromise programming approach to aggregate the objectives in the evaluation step. We adopt a compromise programming formulation that is theoretically able to map the whole Fareto front. The proposed multiobjective m-AINet is tested on the design of a loudspeaker with two objectives, showing promising results.

Original languageEnglish
Article number4526818
Pages (from-to)982-985
Number of pages4
JournalIEEE Transactions on Magnetics
Volume44
Issue number6
DOIs
Publication statusPublished - 1 Jun 2008

Keywords

  • Artificial immune network
  • Compromise programming
  • Multiobjective optimization

Fingerprint

Dive into the research topics of 'Multiobjective optimization using compromise programming and an immune algorithm'. Together they form a unique fingerprint.

Cite this