®®®® SIIA Público

Título del libro: 2015 Ieee Congress On Evolutionary Computation, Cec 2015 - Proceedings
Título del capítulo: GDE-MOEA: A new MOEA based on the Generational Distance indicator and ?-dominance

Autores UNAM:
ADRIANA MENCHACA MENDEZ;
Autores externos:

Idioma:

Año de publicación:
2015
Palabras clave:

Mobility aids for blind persons; Multiobjective optimization; Optimization; Surface reconstruction; Computational costs; High dimensionality; Hypervolume indicators; Multi objective evolutionary algorithms; Multi-objective optimization problem; Objective functions; Selection mechanism; Standard test functions; Evolutionary algorithms


Resumen:

In this paper, we propose a new selection mechanism based on ?-dominance which is called '?-selection'. An interesting feature of this selection scheme is that it does not require to set the value of o ahead of time. Our ?-selection is incorporated into the GD-MOEA algorithm, giving rise to the so-called 'Generational Distance & ?-dominance Multi-Objective Evolutionary Algorithm (GDE-MOEA)'. Our proposed GDE-MOEA is validated using standard test functions taken from the specialized literature, having three to six objective functions. GDE-MOEA is compared with respect to the original GD-MOEA, which is based on the generational distance indicator and a technique based on Euclidean distances to improve the diversity in the population. Additionally, our proposed approach is compared with respect to MOEA/D using Penalty Boundary Intersection (PBI), which is based on decomposition, and SMS-EMOA-HYPE (a version of SMS-EMOA that uses a fitness assignment scheme based on the use of an approximation of the hypervolume indicator). Our preliminary results indicate that our proposed GDE-MOEA is a good alternative to solve multi-objective optimization problems having both low dimensionality and high dimensionality in objective function space because it obtains better results than GD-MOEA and MOEA/D in most cases and it is competitive with respect to SMS-EMOA-HYPE but at a much lower computational cost. © 2015 IEEE.


Entidades citadas de la UNAM: