A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting

Detalhes bibliográficos
Autor(a) principal: Farinati, Davide
Data de Publicação: 2022
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/145478
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
id RCAP_ae924f20a09ca3e10dcd50b285516a97
oai_identifier_str oai:run.unl.pt:10362/145478
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption ForecastingMachine LearningGenetic ProgrammingGeometric Semantic Genetic ProgrammingTime SeriesDissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data ScienceEvolutionary Computation is a sub-field of Machine Learning algorithms based on Darwin’s theory of Evolution. Individuals are evolved using the principles of mutation, crossover and natural selection. One of the most known Evolutionary Algorithms is Genetic Programming (GP), that evolves as individuals computer programs in order to solve regression problems. In this thesis two variations of GP, namely Geometric Semantic Genetic Programming(GSGP) and Tree-based Pipeline Optimization Tool(TPOT), are applied to two energy consumption time series regression problems. Their performance are then compared to state-of-the-art models, LSTM and SVR optimized with DE, and to standard GP. It is showed that the variations of GP outperform standard GP and SVR optimized with DE, while also having comparable performance to LSTM. Additionally a study on the feature selection ability of GSGP is proposed, showing that the algorithm is not actually able to perform feature selection.Vanneschi, LeonardoRUNFarinati, Davide2022-11-14T15:48:34Z2022-10-242022-10-24T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/145478TID:203105630enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:25:52Zoai:run.unl.pt:10362/145478Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:52:05.940209Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
title A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
spellingShingle A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
Farinati, Davide
Machine Learning
Genetic Programming
Geometric Semantic Genetic Programming
Time Series
title_short A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
title_full A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
title_fullStr A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
title_full_unstemmed A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
title_sort A study on variations of Genetic Programming applied to time series forecasting: Machine Learning for Energy Consumption Forecasting
author Farinati, Davide
author_facet Farinati, Davide
author_role author
dc.contributor.none.fl_str_mv Vanneschi, Leonardo
RUN
dc.contributor.author.fl_str_mv Farinati, Davide
dc.subject.por.fl_str_mv Machine Learning
Genetic Programming
Geometric Semantic Genetic Programming
Time Series
topic Machine Learning
Genetic Programming
Geometric Semantic Genetic Programming
Time Series
description Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
publishDate 2022
dc.date.none.fl_str_mv 2022-11-14T15:48:34Z
2022-10-24
2022-10-24T00:00:00Z
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 http://hdl.handle.net/10362/145478
TID:203105630
url http://hdl.handle.net/10362/145478
identifier_str_mv TID:203105630
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.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138112914325504

Registros relacionados