Registro Completo |
Biblioteca(s): |
Embrapa Arroz e Feijão; Embrapa Solos. |
Data corrente: |
12/11/2009 |
Data da última atualização: |
17/05/2022 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
PONTES, M. J. C.; CORTEZ, J.; GALVÃO, R. K. H.; PASQUINI, C.; ARAÚJO, M. C. U.; COELHO, R. M.; CHIBA, M. K.; ABREU, M. F. de; MADARI, B. E. |
Afiliação: |
MÁRCIO JOSÉ COELHO PONTES, Universidade Federal da Paraíba; JULIANA CORTEZ, Unicamp; ROBERTO KAWAKAMI HARROP GALVÃO, Instituto Tecnológico de Aeronáutica; CÉLIO PASQUINI, Unicamp; MÁRIO CÉSAR UGULINO ARAÚJO, Universidade Federal da Paraíba; RICARDO MARQUES COELHO, Instituto Agronômico de Campinas; MÁRCIO KOITI CUNHA, Instituto Agronômico de Campinas; MÔNICA FERREIRA DE ABREU, Instituto Agronômico de Campinas; BEATA EMOKE MADARI, CNPAF. |
Título: |
Classification of Brazilian soils by using LIBS and variable selection in the wavelet domain. |
Ano de publicação: |
2009 |
Fonte/Imprenta: |
Analytica Chimica Acta, v. 642, n. 1/2, p. 12-18, May 2009. |
DOI: |
https://doi.org/10.1016/j.aca.2009.03.001 |
Idioma: |
Inglês |
Conteúdo: |
This paper proposes a novel analytical methodology for soil classification based on the use of laser-induced breakdown spectroscopy (LIBS) and chemometric techniques. In the proposed methodology, linear discriminant analysis (LDA) is employed to build a classification model on the basis of a reduced subset of spectral variables. For the purpose of variable selection, three techniques are considered, namely the successive projection algorithm (SPA), the genetic algorithm (GA), and a stepwise formulation (SW). The use of a data compression procedure in the wavelet domain is also proposed to reduce the computational workload involved in the variable selection process. The methodology is validated in a case study involving the classification of 149 Brazilian soil samples into three different orders (Argissolo, Latossolo and Nitossolo). For means of comparison, soft independent modelling of class analogy (SIMCA) models are also employed. The best discrimination of soil types was attained by SPA-LDA, which achieved an average classification rate of 90% in the validation set and 72% in cross-validation. Moreover, the proposed wavelet compression procedure was found to be of value by providing a 100-fold reduction in computational workload without significantly compromising the classification accuracy of the resulting models. |
Palavras-Chave: |
Wavelet compression. |
Thesagro: |
Classificação do solo. |
Thesaurus Nal: |
Soil classification. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
Marc: |
LEADER 02161naa a2200265 a 4500 001 1574593 005 2022-05-17 008 2009 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.1016/j.aca.2009.03.001$2DOI 100 1 $aPONTES, M. J. C. 245 $aClassification of Brazilian soils by using LIBS and variable selection in the wavelet domain.$h[electronic resource] 260 $c2009 520 $aThis paper proposes a novel analytical methodology for soil classification based on the use of laser-induced breakdown spectroscopy (LIBS) and chemometric techniques. In the proposed methodology, linear discriminant analysis (LDA) is employed to build a classification model on the basis of a reduced subset of spectral variables. For the purpose of variable selection, three techniques are considered, namely the successive projection algorithm (SPA), the genetic algorithm (GA), and a stepwise formulation (SW). The use of a data compression procedure in the wavelet domain is also proposed to reduce the computational workload involved in the variable selection process. The methodology is validated in a case study involving the classification of 149 Brazilian soil samples into three different orders (Argissolo, Latossolo and Nitossolo). For means of comparison, soft independent modelling of class analogy (SIMCA) models are also employed. The best discrimination of soil types was attained by SPA-LDA, which achieved an average classification rate of 90% in the validation set and 72% in cross-validation. Moreover, the proposed wavelet compression procedure was found to be of value by providing a 100-fold reduction in computational workload without significantly compromising the classification accuracy of the resulting models. 650 $aSoil classification 650 $aClassificação do solo 653 $aWavelet compression 700 1 $aCORTEZ, J. 700 1 $aGALVÃO, R. K. H. 700 1 $aPASQUINI, C. 700 1 $aARAÚJO, M. C. U. 700 1 $aCOELHO, R. M. 700 1 $aCHIBA, M. K. 700 1 $aABREU, M. F. de 700 1 $aMADARI, B. E. 773 $tAnalytica Chimica Acta$gv. 642, n. 1/2, p. 12-18, May 2009.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Arroz e Feijão (CNPAF) |
|