Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs

Detalhes bibliográficos
Autor(a) principal: Mariano, Flávia Cristina Martins Queiroz
Data de Publicação: 2020
Outros Autores: Lima, Renato Ribeiro de, Alvarenga, Renata Ribeiro, Rodrigues, Paulo Borges
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFLA
Texto Completo: http://repositorio.ufla.br/jspui/handle/1/48409
Resumo: The objective of this work was to compare the committee neural network (CNN) and weighted multiple linear regression (WMLR) models, in order to estimate the nitrogen-corrected apparent metabolizable energy (AMEn) of poultry feedstuffs. The prediction equation was adjusted by using a WMLR model and the meta-analysis principle. The models were compared by considering the correct prediction percentages, based on the classic prediction intervals and on the highest-probability density intervals, and by using a comparison test for proportions. The accuracy of the models was evaluated based on the values of the mean squared error, coefficient of determination, mean absolute deviation, mean absolute percentage error, and bias. Data from metabolic trials were used to compare the selected models. The committee neural network is the model that showed the highest accuracy of prediction, being recommended as the most accurate model to predict AMEn values for energetic concentrate feedstuffs used by the poultry feed industry.
id UFLA_3583609dd4bee40a9a0d42f2b7ce8c71
oai_identifier_str oai:localhost:1/48409
network_acronym_str UFLA
network_name_str Repositório Institucional da UFLA
repository_id_str
spelling Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffsComitê de redes neurais e regressão múltipla ponderada para a predição de valores energéticos de alimentos para aves de corteCommittee neural networkWeighted multiple linear regressionBroilers - FeedstuffsHighest-probability density intervalMeta-analysisMetabolizable energyRegressão linear múltipla ponderadaFrangos de corte - DietaIntervalo de credibilidade da máxima probabilidadeMeta-análiseEnergia metabolizávelThe objective of this work was to compare the committee neural network (CNN) and weighted multiple linear regression (WMLR) models, in order to estimate the nitrogen-corrected apparent metabolizable energy (AMEn) of poultry feedstuffs. The prediction equation was adjusted by using a WMLR model and the meta-analysis principle. The models were compared by considering the correct prediction percentages, based on the classic prediction intervals and on the highest-probability density intervals, and by using a comparison test for proportions. The accuracy of the models was evaluated based on the values of the mean squared error, coefficient of determination, mean absolute deviation, mean absolute percentage error, and bias. Data from metabolic trials were used to compare the selected models. The committee neural network is the model that showed the highest accuracy of prediction, being recommended as the most accurate model to predict AMEn values for energetic concentrate feedstuffs used by the poultry feed industry.O objetivo deste trabalho foi comparar o modelo comitê de redes neurais e o modelo de regressão linear múltipla ponderada (RLMP), para estimar a energia metabolizável aparente corrigida por nitrogênio (EMAn) de alimentos para aves. A equação de predição foi ajustada por RLMP e pelo princípio da meta-análise. Os modelos foram comparados tendo-se considerando as percentagens de acerto de predição, com base em intervalos de predição clássicos e intervalos de credibilidade da máxima densidade de probabilidade, e utilizado um teste para comparação de proporções. A acurácia dos modelos foi avaliada com base nos valores de erro médio quadrático, coeficiente de determinação, desvio médio absoluto, erro percentual absoluto médio e viés. Dados provenientes de ensaios metabólicos foram utilizados na comparação dos modelos selecionados. O comitê de redes neurais é o modelo que forneceu predições mais acuradas, sendo recomendado como o de maior acurácia, para prever os valores de EMAn de alimentos concentrados utilizados na indústria alimentícia para aves.Embrapa Secretaria de Pesquisa e Desenvolvimento, Pesquisa Agropecuária Brasileira2021-10-26T17:59:21Z2021-10-26T17:59:21Z2020info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfMARIANO, F. C. M. Q. et al. Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs. Pesquisa Agropecuária Brasileira, Brasília, v. 55, e001199, 2020. DOI: 10.1590/S1678-3921.pab2020.v55.001199.http://repositorio.ufla.br/jspui/handle/1/48409Pesquisa Agropecuária Brasileirareponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLAAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessMariano, Flávia Cristina Martins QueirozLima, Renato Ribeiro deAlvarenga, Renata RibeiroRodrigues, Paulo Borgeseng2021-10-26T17:59:22Zoai:localhost:1/48409Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2021-10-26T17:59:22Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false
dc.title.none.fl_str_mv Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
Comitê de redes neurais e regressão múltipla ponderada para a predição de valores energéticos de alimentos para aves de corte
title Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
spellingShingle Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
Mariano, Flávia Cristina Martins Queiroz
Committee neural network
Weighted multiple linear regression
Broilers - Feedstuffs
Highest-probability density interval
Meta-analysis
Metabolizable energy
Regressão linear múltipla ponderada
Frangos de corte - Dieta
Intervalo de credibilidade da máxima probabilidade
Meta-análise
Energia metabolizável
title_short Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
title_full Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
title_fullStr Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
title_full_unstemmed Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
title_sort Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs
author Mariano, Flávia Cristina Martins Queiroz
author_facet Mariano, Flávia Cristina Martins Queiroz
Lima, Renato Ribeiro de
Alvarenga, Renata Ribeiro
Rodrigues, Paulo Borges
author_role author
author2 Lima, Renato Ribeiro de
Alvarenga, Renata Ribeiro
Rodrigues, Paulo Borges
author2_role author
author
author
dc.contributor.author.fl_str_mv Mariano, Flávia Cristina Martins Queiroz
Lima, Renato Ribeiro de
Alvarenga, Renata Ribeiro
Rodrigues, Paulo Borges
dc.subject.por.fl_str_mv Committee neural network
Weighted multiple linear regression
Broilers - Feedstuffs
Highest-probability density interval
Meta-analysis
Metabolizable energy
Regressão linear múltipla ponderada
Frangos de corte - Dieta
Intervalo de credibilidade da máxima probabilidade
Meta-análise
Energia metabolizável
topic Committee neural network
Weighted multiple linear regression
Broilers - Feedstuffs
Highest-probability density interval
Meta-analysis
Metabolizable energy
Regressão linear múltipla ponderada
Frangos de corte - Dieta
Intervalo de credibilidade da máxima probabilidade
Meta-análise
Energia metabolizável
description The objective of this work was to compare the committee neural network (CNN) and weighted multiple linear regression (WMLR) models, in order to estimate the nitrogen-corrected apparent metabolizable energy (AMEn) of poultry feedstuffs. The prediction equation was adjusted by using a WMLR model and the meta-analysis principle. The models were compared by considering the correct prediction percentages, based on the classic prediction intervals and on the highest-probability density intervals, and by using a comparison test for proportions. The accuracy of the models was evaluated based on the values of the mean squared error, coefficient of determination, mean absolute deviation, mean absolute percentage error, and bias. Data from metabolic trials were used to compare the selected models. The committee neural network is the model that showed the highest accuracy of prediction, being recommended as the most accurate model to predict AMEn values for energetic concentrate feedstuffs used by the poultry feed industry.
publishDate 2020
dc.date.none.fl_str_mv 2020
2021-10-26T17:59:21Z
2021-10-26T17:59:21Z
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 MARIANO, F. C. M. Q. et al. Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs. Pesquisa Agropecuária Brasileira, Brasília, v. 55, e001199, 2020. DOI: 10.1590/S1678-3921.pab2020.v55.001199.
http://repositorio.ufla.br/jspui/handle/1/48409
identifier_str_mv MARIANO, F. C. M. Q. et al. Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs. Pesquisa Agropecuária Brasileira, Brasília, v. 55, e001199, 2020. DOI: 10.1590/S1678-3921.pab2020.v55.001199.
url http://repositorio.ufla.br/jspui/handle/1/48409
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Embrapa Secretaria de Pesquisa e Desenvolvimento, Pesquisa Agropecuária Brasileira
publisher.none.fl_str_mv Embrapa Secretaria de Pesquisa e Desenvolvimento, Pesquisa Agropecuária Brasileira
dc.source.none.fl_str_mv Pesquisa Agropecuária Brasileira
reponame:Repositório Institucional da UFLA
instname:Universidade Federal de Lavras (UFLA)
instacron:UFLA
instname_str Universidade Federal de Lavras (UFLA)
instacron_str UFLA
institution UFLA
reponame_str Repositório Institucional da UFLA
collection Repositório Institucional da UFLA
repository.name.fl_str_mv Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)
repository.mail.fl_str_mv nivaldo@ufla.br || repositorio.biblioteca@ufla.br
_version_ 1807835065946734592

Registros relacionados