Grammar Based Evolutionary Design

Detalhes bibliográficos
Autor(a) principal: Assunção, Filipe Guerreiro
Data de Publicação: 2015
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Texto Completo: https://hdl.handle.net/10316/35592
Resumo: Dissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia da Universidade de Coimbra
id RCAP_c8639f8636bbadab424ef31575cd379c
oai_identifier_str oai:estudogeral.uc.pt:10316/35592
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Grammar Based Evolutionary DesignGenetic ProgrammingGrammar EvolutionAlignmentFitness AssignmentDissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia da Universidade de CoimbraA novel evolutionary approach for evolving grammars is presented. It is composed of two main methodologies. In the first one, individuals are represented as a graph, where nodes stand for production rules, and connections between them to the flow of control and parameters. In the second one, a tree representation is used; individuals are derivation trees, from a pre-defined grammar. Inner nodes represent non-terminals, and leaves terminals. It is proved that both representations are able to properly evolve the desired solutions (in this case, images and music). After conducting experiments with the above approaches, running separately, we try to merge components from both of them in order to assess if any improvement is achieved. Graph-mutation has proven to generate the worst results, using both tree and graph-crossovers. When tree-mutation is used the performance obtained with tree and graph-crossovers tends to be similar. Nevertheless, an analysis at a population level, reveals that tree-crossover outperforms the graph one. Considering these results, we searched forms of improving the graph-crossover operator, by means of alignment, thus taking into account the structure of the graphs. Aligning two graphs choosing then the cutting points from the list returned by the algorithm, where the matched pairs of nodes have the least alignment cost, has proven to lead to better performance. Finally, we address the problem of assessing the quality of families of images, proposing a fitness function for the assessment of families of individuals. Families are seen as sets of artifacts that should share common characteristics, allowing one to intuitively classify them as belonging to the same family. Results show the validity of the method and prove that, to evolve a family, both the qualities of the set and of each individual must be taken into consideration.2015-07-20info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesishttps://hdl.handle.net/10316/35592https://hdl.handle.net/10316/35592TID:201537877engAssunção, Filipe Guerreiroinfo:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2022-05-25T04:34:09Zoai:estudogeral.uc.pt:10316/35592Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-29T05:12:55.279272Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Grammar Based Evolutionary Design
title Grammar Based Evolutionary Design
spellingShingle Grammar Based Evolutionary Design
Assunção, Filipe Guerreiro
Genetic Programming
Grammar Evolution
Alignment
Fitness Assignment
title_short Grammar Based Evolutionary Design
title_full Grammar Based Evolutionary Design
title_fullStr Grammar Based Evolutionary Design
title_full_unstemmed Grammar Based Evolutionary Design
title_sort Grammar Based Evolutionary Design
author Assunção, Filipe Guerreiro
author_facet Assunção, Filipe Guerreiro
author_role author
dc.contributor.author.fl_str_mv Assunção, Filipe Guerreiro
dc.subject.por.fl_str_mv Genetic Programming
Grammar Evolution
Alignment
Fitness Assignment
topic Genetic Programming
Grammar Evolution
Alignment
Fitness Assignment
description Dissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia da Universidade de Coimbra
publishDate 2015
dc.date.none.fl_str_mv 2015-07-20
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10316/35592
https://hdl.handle.net/10316/35592
TID:201537877
url https://hdl.handle.net/10316/35592
identifier_str_mv TID:201537877
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833602286176174080

Registros relacionados