|
|
| Acesso ao texto completo restrito à biblioteca da Embrapa Agricultura Digital. Para informações adicionais entre em contato com cnptia.biblioteca@embrapa.br. |
Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital. |
Data corrente: |
14/09/2021 |
Data da última atualização: |
14/09/2021 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
SILVA, J. P. da; ZULLO JÚNIOR, J.; ROMANI, L. A. S. |
Afiliação: |
JOÃO PAULO DA SILVA, Feagri/Unicamp; JURANDIR ZULLO JÚNIOR, UNICAMP; LUCIANA ALVIM SANTOS ROMANI, CNPTIA. |
Título: |
A time series mining approach for agricultural area detection. |
Ano de publicação: |
2020 |
Fonte/Imprenta: |
IEEE Transactions on Big Data, v. 6, n. 3, p. 537-546, Sept. 2020. |
DOI: |
10.1109/TBDATA.2019.2913402 |
Idioma: |
Inglês |
Conteúdo: |
Abstract-Acquiring meaningful data to be employed in building training sets for classification models is a costly task, both in terms of difficult to find suitable samples as well as their quantity. In this sense, Active Learning (AL) improves the training set building by providing an efficient way to select only essential data to be attached to the training set, consequently reducing its size and even enhancing model's accuracy, when compared to random sample selection. In this paper, we proposed a framework for time series classification in order to monitor sugarcane area in Sao Paulo, Brazil. The AL approach consisted of selecting seasonal time series information from less than 1 percent of each class' pixels to build the training set and evaluate this selection by an expert user supported by distance measurements, repeating this process until both distance measurement thresholds were satisfied. In most years, the classification results presented about 90 percent of correlation with official estimates based on both traditional and satellite image analysis methods. This framework can then help Land Use Change (LUC) monitoring as it produced similar results compared to other methods that demands more human and financial resources to be adopted. |
Palavras-Chave: |
Active Learning; Análise de séries temporais; Classificação de pixel; Pixel classification. |
Thesagro: |
Agricultura; Meio Ambiente; Sensoriamento Remoto. |
Thesaurus Nal: |
Agriculture; Environment; Remote sensing; Time series analysis. |
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
Marc: |
LEADER 02133naa a2200289 a 4500 001 2134329 005 2021-09-14 008 2020 bl uuuu u00u1 u #d 024 7 $a10.1109/TBDATA.2019.2913402$2DOI 100 1 $aSILVA, J. P. da 245 $aA time series mining approach for agricultural area detection.$h[electronic resource] 260 $c2020 520 $aAbstract-Acquiring meaningful data to be employed in building training sets for classification models is a costly task, both in terms of difficult to find suitable samples as well as their quantity. In this sense, Active Learning (AL) improves the training set building by providing an efficient way to select only essential data to be attached to the training set, consequently reducing its size and even enhancing model's accuracy, when compared to random sample selection. In this paper, we proposed a framework for time series classification in order to monitor sugarcane area in Sao Paulo, Brazil. The AL approach consisted of selecting seasonal time series information from less than 1 percent of each class' pixels to build the training set and evaluate this selection by an expert user supported by distance measurements, repeating this process until both distance measurement thresholds were satisfied. In most years, the classification results presented about 90 percent of correlation with official estimates based on both traditional and satellite image analysis methods. This framework can then help Land Use Change (LUC) monitoring as it produced similar results compared to other methods that demands more human and financial resources to be adopted. 650 $aAgriculture 650 $aEnvironment 650 $aRemote sensing 650 $aTime series analysis 650 $aAgricultura 650 $aMeio Ambiente 650 $aSensoriamento Remoto 653 $aActive Learning 653 $aAnálise de séries temporais 653 $aClassificação de pixel 653 $aPixel classification 700 1 $aZULLO JÚNIOR, J. 700 1 $aROMANI, L. A. S. 773 $tIEEE Transactions on Big Data$gv. 6, n. 3, p. 537-546, Sept. 2020.
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 Meio-Norte. |
Data corrente: |
29/11/2016 |
Data da última atualização: |
18/05/2022 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Circulação/Nível: |
B - 2 |
Autoria: |
SOUZA, I. G. de B.; SOUZA, V. A. B. de; SILVA, K. J. D. e; LIMA, P. S. da C. |
Afiliação: |
ISIS GOMES DE BRITO SOUZA, UFPI; VALDOMIRO AURÉLIO BARBOSA DE SOUZA, CPAMN; KAESEL JACKSON DAMASCENO E SILVA, CPAMN; PAULO SARMANHO DA COSTA LIMA, CPAMN. |
Título: |
Multivariate analysis of 'bacuri' reproductive and vegetative morphology. |
Título original: |
Análise multivariada da morfologia reprodutiva e vegetativa do bacurizeiro. |
Ano de publicação: |
2016 |
Fonte/Imprenta: |
Comunicata Scientiae, v. 7, n. 2, p. 232-240, 2016. |
DOI: |
10.14295/CS.v7i2.779 |
Idioma: |
Inglês |
Conteúdo: |
The objective of this study was to characterize sixteen genotypes of P. insignis available in the Embrapa Meio-Norte germplasm collection (Teresina, Piauí, Brazil) with respect to 33 morphological traits relating to leaves, flowers, branches, fruits and seeds. Phenotypic variance among genotypes was estimated using the Mahalanobis distance technique and the unweighted pair group method with arithmetic mean analysis (UPGMA). The method of Singh (1981) was used to determine which of the traits contributed most to diversity within genotypes. The occurrence of phenotypic variability among P. insignis genotypes indicated that it would be possible to achieve positive gains with selection. The most distant genotypes were BGB 16 and BGB 48, while crosses between genotype BGB 48 and genotypes BGB 32 and BGB 56 offers the greatest potential as parental types for this fruit tree breeding programs . The flesh content, ovary and fruit length , ratio between fruit length and diameter were the characters that most contributed to diversity among the studied genotypes. |
Palavras-Chave: |
Distância de Mahalanobis; Diversidade fenotípica. |
Thesagro: |
Platonia Insignis. |
Categoria do assunto: |
G Melhoramento Genético |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/150775/1/ArtigoSarmanhoComunicata2016.pdf
|
Marc: |
LEADER 01799naa a2200217 a 4500 001 2057376 005 2022-05-18 008 2016 bl uuuu u00u1 u #d 024 7 $a10.14295/CS.v7i2.779$2DOI 100 1 $aSOUZA, I. G. de B. 240 $aAnálise multivariada da morfologia reprodutiva e vegetativa do bacurizeiro. 245 $aMultivariate analysis of 'bacuri' reproductive and vegetative morphology.$h[electronic resource] 260 $c2016 520 $aThe objective of this study was to characterize sixteen genotypes of P. insignis available in the Embrapa Meio-Norte germplasm collection (Teresina, Piauí, Brazil) with respect to 33 morphological traits relating to leaves, flowers, branches, fruits and seeds. Phenotypic variance among genotypes was estimated using the Mahalanobis distance technique and the unweighted pair group method with arithmetic mean analysis (UPGMA). The method of Singh (1981) was used to determine which of the traits contributed most to diversity within genotypes. The occurrence of phenotypic variability among P. insignis genotypes indicated that it would be possible to achieve positive gains with selection. The most distant genotypes were BGB 16 and BGB 48, while crosses between genotype BGB 48 and genotypes BGB 32 and BGB 56 offers the greatest potential as parental types for this fruit tree breeding programs . The flesh content, ovary and fruit length , ratio between fruit length and diameter were the characters that most contributed to diversity among the studied genotypes. 650 $aPlatonia Insignis 653 $aDistância de Mahalanobis 653 $aDiversidade fenotípica 700 1 $aSOUZA, V. A. B. de 700 1 $aSILVA, K. J. D. e 700 1 $aLIMA, P. S. da C. 773 $tComunicata Scientiae$gv. 7, n. 2, p. 232-240, 2016.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Meio-Norte (CPAMN) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Expressão de busca inválida. Verifique!!! |
|
|