Artificial neural network to estimate the basic density of cerrado wood
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Pesquisa Florestal Brasileira (Online) |
Texto Completo: | https://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/1656 |
Resumo: | The basic density of wood is an important property because it is related to the final product in the various uses that wood has. However, its determination demands time and costs, which justifies the use of more refined techniques for its estimation, such as artificial neural networks (ANN). The objective was to evaluate the use of artificial neural networks to estimate the basic density of species of cerrado stricto sensu with the use of Pilodyn and dendrometric variables. To compare the results obtained by ANN, regression models were adjusted. The best performing neural network was the one that used as input variables the depth of penetration (Pilodyn), species and DAP, presenting R² values of 0.72 and with root mean square error in percentage (RMSE%) of 5.69. The regression model presented R² value of 0.72 and RMSE% of 9.19. The artificial neural networks can estimate the basic wood density of species of cerrado stricto sensu studied in this study with satisfactory results. |
id |
EMBRAPA-5_6ae6f8b20a3d1ff029042940397d14fa |
---|---|
oai_identifier_str |
oai:pfb.cnpf.embrapa.br/pfb:article/1656 |
network_acronym_str |
EMBRAPA-5 |
network_name_str |
Pesquisa Florestal Brasileira (Online) |
repository_id_str |
|
spelling |
Artificial neural network to estimate the basic density of cerrado woodRedes neurais artificiais para estimar a densidade básica de madeiras do cerradoArtificial intelligenceWood densityPilodynInteligência artificialDensidade da madeiraPilodynThe basic density of wood is an important property because it is related to the final product in the various uses that wood has. However, its determination demands time and costs, which justifies the use of more refined techniques for its estimation, such as artificial neural networks (ANN). The objective was to evaluate the use of artificial neural networks to estimate the basic density of species of cerrado stricto sensu with the use of Pilodyn and dendrometric variables. To compare the results obtained by ANN, regression models were adjusted. The best performing neural network was the one that used as input variables the depth of penetration (Pilodyn), species and DAP, presenting R² values of 0.72 and with root mean square error in percentage (RMSE%) of 5.69. The regression model presented R² value of 0.72 and RMSE% of 9.19. The artificial neural networks can estimate the basic wood density of species of cerrado stricto sensu studied in this study with satisfactory results.A densidade básica da madeira é uma propriedade importante, pois está relacionada ao produto final nos diversos usos que a madeira possui. Porém, sua determinação demanda tempo e custos, o que justifica o emprego de técnicas mais refinadas para a sua estimação, como as redes neurais artificias (RNA). Objetivou-se avaliar a utilização das RNA para estimar a densidade básica de espécies do cerrado sensu stricto com o uso do aparelho Pilodyn e variáveis dendrométricas. Para comparação dos resultados obtidos pelas RNA, foram ajustados modelos de regressão. A rede neural com melhor desempenho foi a que utilizou como variáveis de entrada a profundidade de penetração (Pilodyn), espécie e o DAP, apresentando valores de R² de 0,72 e com raiz do erro quadrado médio em porcentagem (RMSE%) de 5,69. Já o modelo de regressão apresentou valor de R² de 0,72 e RMSE% de 9,19. As redes neurais artificiais conseguem estimar a densidade básica da madeira de espécies do cerrado stricto sensu com resultados satisfatórios.Embrapa Florestas2018-12-29info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/165610.4336/2018.pfb.38e201801656Pesquisa Florestal Brasileira; v. 38 (2018)Pesquisa Florestal Brasileira; Vol. 38 (2018)1983-26051809-3647reponame:Pesquisa Florestal Brasileira (Online)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPAporhttps://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/1656/825Silva, Jeferson Pereira MartinsCabacinha, Christian DiasAssis, Adriana LeandraMonteiro, Thiago CamposAraújo Júnior, Carlos AlbertoMaia, Renato Douradoinfo:eu-repo/semantics/openAccess2019-05-10T19:43:47Zoai:pfb.cnpf.embrapa.br/pfb:article/1656Revistahttps://pfb.cnpf.embrapa.br/pfb/index.php/pfb/PUBhttps://pfb.cnpf.embrapa.br/pfb/index.php/pfb/oaipfb@embrapa.br || revista.pfb@gmail.com || patricia.mattos@embrapa.br1983-26051809-3647opendoar:2019-05-10T19:43:47Pesquisa Florestal Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Artificial neural network to estimate the basic density of cerrado wood Redes neurais artificiais para estimar a densidade básica de madeiras do cerrado |
title |
Artificial neural network to estimate the basic density of cerrado wood |
spellingShingle |
Artificial neural network to estimate the basic density of cerrado wood Silva, Jeferson Pereira Martins Artificial intelligence Wood density Pilodyn Inteligência artificial Densidade da madeira Pilodyn |
title_short |
Artificial neural network to estimate the basic density of cerrado wood |
title_full |
Artificial neural network to estimate the basic density of cerrado wood |
title_fullStr |
Artificial neural network to estimate the basic density of cerrado wood |
title_full_unstemmed |
Artificial neural network to estimate the basic density of cerrado wood |
title_sort |
Artificial neural network to estimate the basic density of cerrado wood |
author |
Silva, Jeferson Pereira Martins |
author_facet |
Silva, Jeferson Pereira Martins Cabacinha, Christian Dias Assis, Adriana Leandra Monteiro, Thiago Campos Araújo Júnior, Carlos Alberto Maia, Renato Dourado |
author_role |
author |
author2 |
Cabacinha, Christian Dias Assis, Adriana Leandra Monteiro, Thiago Campos Araújo Júnior, Carlos Alberto Maia, Renato Dourado |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Silva, Jeferson Pereira Martins Cabacinha, Christian Dias Assis, Adriana Leandra Monteiro, Thiago Campos Araújo Júnior, Carlos Alberto Maia, Renato Dourado |
dc.subject.por.fl_str_mv |
Artificial intelligence Wood density Pilodyn Inteligência artificial Densidade da madeira Pilodyn |
topic |
Artificial intelligence Wood density Pilodyn Inteligência artificial Densidade da madeira Pilodyn |
description |
The basic density of wood is an important property because it is related to the final product in the various uses that wood has. However, its determination demands time and costs, which justifies the use of more refined techniques for its estimation, such as artificial neural networks (ANN). The objective was to evaluate the use of artificial neural networks to estimate the basic density of species of cerrado stricto sensu with the use of Pilodyn and dendrometric variables. To compare the results obtained by ANN, regression models were adjusted. The best performing neural network was the one that used as input variables the depth of penetration (Pilodyn), species and DAP, presenting R² values of 0.72 and with root mean square error in percentage (RMSE%) of 5.69. The regression model presented R² value of 0.72 and RMSE% of 9.19. The artificial neural networks can estimate the basic wood density of species of cerrado stricto sensu studied in this study with satisfactory results. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-29 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/1656 10.4336/2018.pfb.38e201801656 |
url |
https://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/1656 |
identifier_str_mv |
10.4336/2018.pfb.38e201801656 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/1656/825 |
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 |
Embrapa Florestas |
publisher.none.fl_str_mv |
Embrapa Florestas |
dc.source.none.fl_str_mv |
Pesquisa Florestal Brasileira; v. 38 (2018) Pesquisa Florestal Brasileira; Vol. 38 (2018) 1983-2605 1809-3647 reponame:Pesquisa Florestal Brasileira (Online) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Pesquisa Florestal Brasileira (Online) |
collection |
Pesquisa Florestal Brasileira (Online) |
repository.name.fl_str_mv |
Pesquisa Florestal Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
pfb@embrapa.br || revista.pfb@gmail.com || patricia.mattos@embrapa.br |
_version_ |
1783370936784781312 |