|
|
Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital. |
Data corrente: |
13/02/2019 |
Data da última atualização: |
13/02/2019 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
FARHATE, C. V. V.; SOUZA, Z. M. de; OLIVEIRA, S. R. de M.; CARVALHO, J. L. N.; LA SCALA JÚNIOR, N.; SANTOS, A. P. G. |
Afiliação: |
CAMILA VIANA VIEIRA FARHATE, Feagri/Unicamp; ZIGOMAR MENEZES DE SOUZA, Feagri/Unicamp; STANLEY ROBSON DE MEDEIROS OLIVEIRA, CNPTIA, Feagri/Unicamp; JOÃO LUÍS NUNES CARVALHO, CNPEM; NEWTON LA SCALA JÚNIOR, Unesp; ANA PAULA GUIMARÃES SANTOS, Feagri/Unicamp. |
Título: |
Classification of soil respiration in areas of sugarcane renewal using decision tree. |
Ano de publicação: |
2018 |
Fonte/Imprenta: |
Scientia Agricola, v. 75, n. 3, p. 216-224, May/June 2018. |
DOI: |
http://dx.doi.org/10.1590/1678-992X-2016-0473 |
Idioma: |
Inglês |
Conteúdo: |
ABSTRACT: The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response) variable). The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS), chisquare method (χ2) and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipitation > macroporosity > soil moisture > potential acidity. MenosABSTRACT: The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response) variable). The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS), chisquare method (χ2) and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipi... Mostrar Tudo |
Palavras-Chave: |
Árvore de decisão; Data mining; Decision tree; Emissão de gás carbônico no solo; Matéria orgânica no solo; Mineração de dados; Seleção de variável; Temperatura no solo; Variable selection. |
Thesagro: |
Respiração do Solo. |
Thesaurus Nal: |
Carbon dioxide; Soil organic matter; Soil temperature. |
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/192660/1/AP-Classification-soil-Farhate.pdf
|
Marc: |
LEADER 02675naa a2200349 a 4500 001 2105884 005 2019-02-13 008 2018 bl uuuu u00u1 u #d 024 7 $ahttp://dx.doi.org/10.1590/1678-992X-2016-0473$2DOI 100 1 $aFARHATE, C. V. V. 245 $aClassification of soil respiration in areas of sugarcane renewal using decision tree.$h[electronic resource] 260 $c2018 520 $aABSTRACT: The use of data mining is a promising alternative to predict soil respiration from correlated variables. Our objective was to build a model using variable selection and decision tree induction to predict different levels of soil respiration, taking into account physical, chemical and microbiological variables of soil as well as precipitation in renewal of sugarcane areas. The original dataset was composed of 19 variables (18 independent variables and one dependent (or response) variable). The variable-target refers to soil respiration as the target classification. Due to a large number of variables, a procedure for variable selection was conducted to remove those with low correlation with the variable-target. For that purpose, four approaches of variable selection were evaluated: no variable selection, correlation-based feature selection (CFS), chisquare method (χ2) and Wrapper. To classify soil respiration, we used the decision tree induction technique available in the Weka software package. Our results showed that data mining techniques allow the development of a model for soil respiration classification with accuracy of 81 %, resulting in a knowledge base composed of 27 rules for prediction of soil respiration. In particular, the wrapper method for variable selection identified a subset of only five variables out of 18 available in the original dataset, and they had the following order of influence in determining soil respiration: soil temperature > precipitation > macroporosity > soil moisture > potential acidity. 650 $aCarbon dioxide 650 $aSoil organic matter 650 $aSoil temperature 650 $aRespiração do Solo 653 $aÁrvore de decisão 653 $aData mining 653 $aDecision tree 653 $aEmissão de gás carbônico no solo 653 $aMatéria orgânica no solo 653 $aMineração de dados 653 $aSeleção de variável 653 $aTemperatura no solo 653 $aVariable selection 700 1 $aSOUZA, Z. M. de 700 1 $aOLIVEIRA, S. R. de M. 700 1 $aCARVALHO, J. L. N. 700 1 $aLA SCALA JÚNIOR, N. 700 1 $aSANTOS, A. P. G. 773 $tScientia Agricola$gv. 75, n. 3, p. 216-224, May/June 2018.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registro Completo
Biblioteca(s): |
Embrapa Mandioca e Fruticultura. |
Data corrente: |
05/11/2012 |
Data da última atualização: |
05/11/2012 |
Tipo da produção científica: |
Resumo em Anais de Congresso |
Autoria: |
ANDRADE, W. B. de; PEIXOUTO, Y. S.; VILARINHOS, A. D.; HADDAD, F.; OLIVEIRA, S. A. S. de; FERREIRA, C. F. |
Afiliação: |
WILMA BRANDÃO DE ANDRADE, Fapesb; YSLAI SILVA PEIXOUTO, UFRB; ALBERTO DUARTE VILARINHOS, CNPMF; FERNANDO HADDAD, CNPMF; SAULO ALVES SANTOS DE OLIVEIRA, CNPMF; CLAUDIA FORTES FERREIRA, CNPMF. |
Título: |
Construção de micoteca de Mycosphaerella musicola no Estado da Bahia. |
Ano de publicação: |
2012 |
Fonte/Imprenta: |
In: JORNADA CIENTÍFICA EMBRAPA MANDIOCA E FRUTICULTURA, 6., 2012, Cruz das Almas. Anais... Cruz das Almas: Embrapa Mandioca e Fruticultura, 2012. |
Idioma: |
Português |
Conteúdo: |
A cultura da bananeira assume importância econômica e social em todo o mundo sendo cultivada em mais de 130 países tropicais e subtropicais, principalmente por pequenos agricultores. No Brasil, a Região Nordeste se destaca, representando 40% da produção nacional e o Estado da Bahia se posiciona em primeiro lugar, sendo responsável pela renda de milhões de famílias no nordeste do país. |
Palavras-Chave: |
Coleção fúngica; Sigatoka-amarela. |
Thesaurus NAL: |
Mycosphaerella. |
Categoria do assunto: |
-- |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/69404/1/084-12-Wilma-Vilarinhos.pdf
|
Marc: |
LEADER 01105nam a2200205 a 4500 001 1938900 005 2012-11-05 008 2012 bl uuuu u00u1 u #d 100 1 $aANDRADE, W. B. de 245 $aConstrução de micoteca de Mycosphaerella musicola no Estado da Bahia.$h[electronic resource] 260 $aIn: JORNADA CIENTÍFICA EMBRAPA MANDIOCA E FRUTICULTURA, 6., 2012, Cruz das Almas. Anais... Cruz das Almas: Embrapa Mandioca e Fruticultura$c2012 520 $aA cultura da bananeira assume importância econômica e social em todo o mundo sendo cultivada em mais de 130 países tropicais e subtropicais, principalmente por pequenos agricultores. No Brasil, a Região Nordeste se destaca, representando 40% da produção nacional e o Estado da Bahia se posiciona em primeiro lugar, sendo responsável pela renda de milhões de famílias no nordeste do país. 650 $aMycosphaerella 653 $aColeção fúngica 653 $aSigatoka-amarela 700 1 $aPEIXOUTO, Y. S. 700 1 $aVILARINHOS, A. D. 700 1 $aHADDAD, F. 700 1 $aOLIVEIRA, S. A. S. de 700 1 $aFERREIRA, C. F.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Mandioca e Fruticultura (CNPMF) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|