Study of stem form using artificial neural networks and taper functions

Detalhes bibliográficos
Autor(a) principal: Schikowski, Ana Beatriz
Data de Publicação: 2015
Outros Autores: Dalla Corte, Ana Paula, Sanquetta, Carlos Roberto
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/867
Resumo: Artificial neural networks (ANN) have great potential as an alternative to conventional regression analysis because of its learning capacity of data set information and the generalization of learning to unknown data. So, the aim of this study was to apply RNAs to estimate relative diameter, total and commercial volume, as well as to compare their performance in relation to conventional taper functions. Data from 47 trees of Eucalyptus sp. were used in the training and validation of ANNs and in adjusting Hradetzky and Garay taper functions. The performance of ANNs were similar to the taper functions for diameter estimative, furthermore the estimative of commercial and total volume applying ANNs were more accurate and presented less residues scattering than Garay and Hradetzky function. ANNs were accurate and appropriate for the estimation of volume and relative diameter.
id EMBRAPA-5_5e987c0a1c96ee79a45c8f8c3b9494cc
oai_identifier_str oai:pfb.cnpf.embrapa.br/pfb:article/867
network_acronym_str EMBRAPA-5
network_name_str Pesquisa Florestal Brasileira (Online)
repository_id_str
spelling Study of stem form using artificial neural networks and taper functionsEstudo da forma do fuste utilizando redes neurais artificiais e funções de afilamentoCubageEucalyptArtificial intelligenceCubagemEucaliptoInteligência artificialArtificial neural networks (ANN) have great potential as an alternative to conventional regression analysis because of its learning capacity of data set information and the generalization of learning to unknown data. So, the aim of this study was to apply RNAs to estimate relative diameter, total and commercial volume, as well as to compare their performance in relation to conventional taper functions. Data from 47 trees of Eucalyptus sp. were used in the training and validation of ANNs and in adjusting Hradetzky and Garay taper functions. The performance of ANNs were similar to the taper functions for diameter estimative, furthermore the estimative of commercial and total volume applying ANNs were more accurate and presented less residues scattering than Garay and Hradetzky function. ANNs were accurate and appropriate for the estimation of volume and relative diameter.As redes neurais artificiais (RNA) possuem grande potencial como alternativa à análise de regressão convencional, dada a capacidade de aprendizado de informações de um conjunto de dados e a generalização desse aprendizado para dados desconhecidos. Nesse sentido, o objetivo do presente trabalho foi utilizar RNAs para a estimativa do diâmetro relativo, volume total e comercial, bem como a comparação do desempenho em relação a funções de afilamento convencionais. Dados provenientes de 47 árvores de Eucalyptus sp. foram utilizados no treinamento e validação das RNAs e no ajuste das funções de afilamento de Hradetzky e Garay. O desempenho das RNAs foi muito semelhante ao das funções de afilamento na estimava do diâmetro relativo. As estimativas de volume total e comercial com RNAs se mostraram mais precisas e com menor dispersão dos resíduos que Hradetzky e Garay. RNAs se mostraram acuradas e adequadas para a estimativa de diâmetro relativo e volume.Embrapa Florestas2015-06-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/86710.4336/2015.pfb.35.82.867Pesquisa Florestal Brasileira; v. 35 n. 82 (2015): abr./jun.; 119-127Pesquisa Florestal Brasileira; Vol. 35 No. 82 (2015): abr./jun.; 119-1271983-26051809-3647reponame:Pesquisa Florestal Brasileira (Online)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPAporhttps://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/867/412Copyright (c) 2015 Ana Beatriz Schikowski, Ana Paula Dalla Corte, Carlos Roberto Sanquettahttps://creativecommons.org/licenses/by-nc-nd/4.0info:eu-repo/semantics/openAccessSchikowski, Ana BeatrizDalla Corte, Ana PaulaSanquetta, Carlos Roberto2017-04-28T12:44:45Zoai:pfb.cnpf.embrapa.br/pfb:article/867Revistahttps://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:2017-04-28T12:44:45Pesquisa Florestal Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false
dc.title.none.fl_str_mv Study of stem form using artificial neural networks and taper functions
Estudo da forma do fuste utilizando redes neurais artificiais e funções de afilamento
title Study of stem form using artificial neural networks and taper functions
spellingShingle Study of stem form using artificial neural networks and taper functions
Schikowski, Ana Beatriz
Cubage
Eucalypt
Artificial intelligence
Cubagem
Eucalipto
Inteligência artificial
title_short Study of stem form using artificial neural networks and taper functions
title_full Study of stem form using artificial neural networks and taper functions
title_fullStr Study of stem form using artificial neural networks and taper functions
title_full_unstemmed Study of stem form using artificial neural networks and taper functions
title_sort Study of stem form using artificial neural networks and taper functions
author Schikowski, Ana Beatriz
author_facet Schikowski, Ana Beatriz
Dalla Corte, Ana Paula
Sanquetta, Carlos Roberto
author_role author
author2 Dalla Corte, Ana Paula
Sanquetta, Carlos Roberto
author2_role author
author
dc.contributor.author.fl_str_mv Schikowski, Ana Beatriz
Dalla Corte, Ana Paula
Sanquetta, Carlos Roberto
dc.subject.por.fl_str_mv Cubage
Eucalypt
Artificial intelligence
Cubagem
Eucalipto
Inteligência artificial
topic Cubage
Eucalypt
Artificial intelligence
Cubagem
Eucalipto
Inteligência artificial
description Artificial neural networks (ANN) have great potential as an alternative to conventional regression analysis because of its learning capacity of data set information and the generalization of learning to unknown data. So, the aim of this study was to apply RNAs to estimate relative diameter, total and commercial volume, as well as to compare their performance in relation to conventional taper functions. Data from 47 trees of Eucalyptus sp. were used in the training and validation of ANNs and in adjusting Hradetzky and Garay taper functions. The performance of ANNs were similar to the taper functions for diameter estimative, furthermore the estimative of commercial and total volume applying ANNs were more accurate and presented less residues scattering than Garay and Hradetzky function. ANNs were accurate and appropriate for the estimation of volume and relative diameter.
publishDate 2015
dc.date.none.fl_str_mv 2015-06-30
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/867
10.4336/2015.pfb.35.82.867
url https://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/867
identifier_str_mv 10.4336/2015.pfb.35.82.867
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/867/412
dc.rights.driver.fl_str_mv Copyright (c) 2015 Ana Beatriz Schikowski, Ana Paula Dalla Corte, Carlos Roberto Sanquetta
https://creativecommons.org/licenses/by-nc-nd/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2015 Ana Beatriz Schikowski, Ana Paula Dalla Corte, Carlos Roberto Sanquetta
https://creativecommons.org/licenses/by-nc-nd/4.0
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. 35 n. 82 (2015): abr./jun.; 119-127
Pesquisa Florestal Brasileira; Vol. 35 No. 82 (2015): abr./jun.; 119-127
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_ 1783370935270637568

Registros relacionados