Evolutionary optimization in dynamic fitness landscape environments

Non-stationary, or dynamic, problems change over time. There exist a variety of forms of dynamism. The concept of dynamic environments in the context of this paper means that the fitness landscape changes during the run of an evolutionary algorithm. Genetic diversity is crucial to provide the neces...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Aragón, Victoria S., Esquivel, Susana Cecilia
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2003
Materias:
Ciencias Informáticas
Evolutionary computation
multi-modal optimization
random inmigrants
macromutation
dynamic fitness landscape
Environments
Optimization
ARTIFICIAL INTELLIGENCE
Intelligent agents
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/22732
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-22732
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Evolutionary computation
multi-modal optimization
random inmigrants
macromutation
dynamic fitness landscape
Environments
Optimization
ARTIFICIAL INTELLIGENCE
Intelligent agents
spellingShingle Ciencias Informáticas
Evolutionary computation
multi-modal optimization
random inmigrants
macromutation
dynamic fitness landscape
Environments
Optimization
ARTIFICIAL INTELLIGENCE
Intelligent agents
Aragón, Victoria S.
Esquivel, Susana Cecilia
Evolutionary optimization in dynamic fitness landscape environments
topic_facet Ciencias Informáticas
Evolutionary computation
multi-modal optimization
random inmigrants
macromutation
dynamic fitness landscape
Environments
Optimization
ARTIFICIAL INTELLIGENCE
Intelligent agents
description Non-stationary, or dynamic, problems change over time. There exist a variety of forms of dynamism. The concept of dynamic environments in the context of this paper means that the fitness landscape changes during the run of an evolutionary algorithm. Genetic diversity is crucial to provide the necessary adaptability of the algorithm to unexpected changes. Two key concepts to maintain genetic diversity in the population are incorporated to the algorithm and proposed here: macromutation operators and random immigrants. The algorithm was tested on a set of dynamic testing functions provided by a dynamic fitness problem generator. The main goal was to determine the algorithm ability to face changes and dimensional or multimodal scalability in the functions. The effectiveness and limitations of the proposed algorithm in diverse scenarios of a dynamic environment is discussed from results empirically obtained.
format Objeto de conferencia
Objeto de conferencia
author Aragón, Victoria S.
Esquivel, Susana Cecilia
author_facet Aragón, Victoria S.
Esquivel, Susana Cecilia
author_sort Aragón, Victoria S.
title Evolutionary optimization in dynamic fitness landscape environments
title_short Evolutionary optimization in dynamic fitness landscape environments
title_full Evolutionary optimization in dynamic fitness landscape environments
title_fullStr Evolutionary optimization in dynamic fitness landscape environments
title_full_unstemmed Evolutionary optimization in dynamic fitness landscape environments
title_sort evolutionary optimization in dynamic fitness landscape environments
publishDate 2003
url http://sedici.unlp.edu.ar/handle/10915/22732
work_keys_str_mv AT aragonvictorias evolutionaryoptimizationindynamicfitnesslandscapeenvironments
AT esquivelsusanacecilia evolutionaryoptimizationindynamicfitnesslandscapeenvironments
bdutipo_str Repositorios
_version_ 1764820467602948097

Ejemplares similares