Performance assessment of an artificial immune system multiobjective optimizer by two improved metrics

Authors:
Maoguo Gong;Licheng Jiao;Haifeng Du;Ronghua Shang;Bin Lu
Affiliations:
Xidian University, Xi'an, China;Xidian University, Xi'an, China;Xi'an Jiaotong University, Xi'an, China;Xidian University, Xi'an, China;Xidian University, Xi'an, China
Venue:
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Year:
2005

Citing 2
Cited 0

Multiobjective evolutionary algorithms: classifications, analyses, and new innovations

Multiobjective evolutionary algorithms: classifications, analyses, and new innovations
Clonal selection with immune dominance and anergy based multiobjective optimization

EMO'05 Proceedings of the Third international conference on Evolutionary Multi-Criterion Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, we introduce two improved assessment metrics of multiobjective optimizers, Nondominated Ratio and Spacing Distribution, and analyze their rationality and validity. Based on the concept of Immunodominance and Antibody Clonal Selection Theory, a novel multiobjective optimization algorithm, Immune Dominance Clonal Multiobjective Algorithm (IDCMA), is put forward. The simulation comparisons between IDCMA and the Strength Pareto Evolutionary Algorithm show that IDCMA has the best performance in popular metrics such as Spacing, Coverage of Two Sets and the two new metrics presented in this paper when low-dimensional multiobjective problems are concerned. The statistical results of the four metrics also show that Spacing Distribution conquers some limitations of Spacing triumphantly, and Nondominated Ratio conquers the limitation of Coverage of Two Sets that only compared between two sets.