Multilayer perceptron network optimization for chaotic time series modeling
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/1822/86985 |
Resumo: | Chaotic time series are widely present in practice, but due to their characteristics—such as internal randomness, nonlinearity, and long-term unpredictability—it is difficult to achieve high-precision intermediate or long-term predictions. Multi-layer perceptron (MLP) networks are an effective tool for chaotic time series modeling. Focusing on chaotic time series modeling, this paper presents a generalized degree of freedom approximation method of MLP. We then obtain its Akachi information criterion, which is designed as the loss function for training, hence developing an overall framework for chaotic time series analysis, including phase space reconstruction, model training, and model selection. To verify the effectiveness of the proposed method, it is applied to two artificial chaotic time series and two real-world chaotic time series. The numerical results show that the proposed optimized method is effective to obtain the best model from a group of candidates. Moreover, the optimized models perform very well in multi-step prediction tasks. |
id |
RCAP_3fae717099a261b7e81d2dcf27cb0ad5 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/86985 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Multilayer perceptron network optimization for chaotic time series modelingChaotic time seriesMultilayer perceptron networkGeneralized degrees of freedomAkaike information criterionMaximal Lyapunov exponentChaotic time series are widely present in practice, but due to their characteristics—such as internal randomness, nonlinearity, and long-term unpredictability—it is difficult to achieve high-precision intermediate or long-term predictions. Multi-layer perceptron (MLP) networks are an effective tool for chaotic time series modeling. Focusing on chaotic time series modeling, this paper presents a generalized degree of freedom approximation method of MLP. We then obtain its Akachi information criterion, which is designed as the loss function for training, hence developing an overall framework for chaotic time series analysis, including phase space reconstruction, model training, and model selection. To verify the effectiveness of the proposed method, it is applied to two artificial chaotic time series and two real-world chaotic time series. The numerical results show that the proposed optimized method is effective to obtain the best model from a group of candidates. Moreover, the optimized models perform very well in multi-step prediction tasks.This research was funded in part by the NSFC grant numbers 61972174 and 62272192, the Science-Technology Development Plan Project of Jilin Province grant number 20210201080GX, the Jilin Province Development and Reform Commission grant number 2021C044-1, the Guangdong Universities’ Innovation Team grant number 2021KCXTD015, and Key Disciplines Projects grant number 2021ZDJS138.Multidisciplinary Digital Publishing Institute (MDPI)Universidade do MinhoMu QiaoYanchun LiangTavares, AdrianoXiaohu Shi2023-06-242023-06-24T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/1822/86985engQiao, M.; Liang, Y.; Tavares, A.; Shi, X. Multilayer Perceptron Network Optimization for Chaotic Time Series Modeling. Entropy 2023, 25, 973. https://doi.org/10.3390/e250709731099-430010.3390/e25070973https://www.mdpi.com/1099-4300/25/7/973info: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:RCAAP2023-12-02T01:20:55Zoai:repositorium.sdum.uminho.pt:1822/86985Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:39:07.083740Repositório 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 |
Multilayer perceptron network optimization for chaotic time series modeling |
title |
Multilayer perceptron network optimization for chaotic time series modeling |
spellingShingle |
Multilayer perceptron network optimization for chaotic time series modeling Mu Qiao Chaotic time series Multilayer perceptron network Generalized degrees of freedom Akaike information criterion Maximal Lyapunov exponent |
title_short |
Multilayer perceptron network optimization for chaotic time series modeling |
title_full |
Multilayer perceptron network optimization for chaotic time series modeling |
title_fullStr |
Multilayer perceptron network optimization for chaotic time series modeling |
title_full_unstemmed |
Multilayer perceptron network optimization for chaotic time series modeling |
title_sort |
Multilayer perceptron network optimization for chaotic time series modeling |
author |
Mu Qiao |
author_facet |
Mu Qiao Yanchun Liang Tavares, Adriano Xiaohu Shi |
author_role |
author |
author2 |
Yanchun Liang Tavares, Adriano Xiaohu Shi |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Mu Qiao Yanchun Liang Tavares, Adriano Xiaohu Shi |
dc.subject.por.fl_str_mv |
Chaotic time series Multilayer perceptron network Generalized degrees of freedom Akaike information criterion Maximal Lyapunov exponent |
topic |
Chaotic time series Multilayer perceptron network Generalized degrees of freedom Akaike information criterion Maximal Lyapunov exponent |
description |
Chaotic time series are widely present in practice, but due to their characteristics—such as internal randomness, nonlinearity, and long-term unpredictability—it is difficult to achieve high-precision intermediate or long-term predictions. Multi-layer perceptron (MLP) networks are an effective tool for chaotic time series modeling. Focusing on chaotic time series modeling, this paper presents a generalized degree of freedom approximation method of MLP. We then obtain its Akachi information criterion, which is designed as the loss function for training, hence developing an overall framework for chaotic time series analysis, including phase space reconstruction, model training, and model selection. To verify the effectiveness of the proposed method, it is applied to two artificial chaotic time series and two real-world chaotic time series. The numerical results show that the proposed optimized method is effective to obtain the best model from a group of candidates. Moreover, the optimized models perform very well in multi-step prediction tasks. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-06-24 2023-06-24T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/1822/86985 |
url |
https://hdl.handle.net/1822/86985 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Qiao, M.; Liang, Y.; Tavares, A.; Shi, X. Multilayer Perceptron Network Optimization for Chaotic Time Series Modeling. Entropy 2023, 25, 973. https://doi.org/10.3390/e25070973 1099-4300 10.3390/e25070973 https://www.mdpi.com/1099-4300/25/7/973 |
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.publisher.none.fl_str_mv |
Multidisciplinary Digital Publishing Institute (MDPI) |
publisher.none.fl_str_mv |
Multidisciplinary Digital Publishing Institute (MDPI) |
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_ |
1799133651533824000 |