| |
|
|
| Registros recuperados : 199 | |
| Registros recuperados : 199 | |
|
|
|
Registro Completo
|
Biblioteca(s): |
Embrapa Territorial. |
|
Data corrente: |
10/01/2023 |
|
Data da última atualização: |
10/01/2023 |
|
Tipo da produção científica: |
Artigo em Anais de Congresso |
|
Autoria: |
SILVA, M. A. S. da; MATOS, L. N.; SANTOS, F. E. DE O.; DOMPIERI, M. H. G.; MOURA, F. R. DE. |
|
Afiliação: |
MARCOS AURELIO SANTOS DA SILVA, CPATC; LEONARDO NOGUEIRA MATOS, UNIVERSIDADE FEDERAL DE SERGIPE; FLÁVIO EMANUEL DE OLIVEIRA SANTOS, UNIVERSIDADE FEDERAL DE SERGIPE; MARCIA HELENA GALINA DOMPIERI, CNPM; FÁBIO RODRIGUES DE MOURA, UNIVERSIDADE FEDERAL DE SERGIPE. |
|
Título: |
Feature extraction of spatial panel data with autoencoders for clustering the Brazilian agricultural diversity. |
|
Ano de publicação: |
2022 |
|
Fonte/Imprenta: |
In: BRAZILIAN SYMPOSIUM ON GEOINFORMATICS, 22., 2022, São José dos Campos. Proceedings... São José dos Campos: MCTIC/INPE, 2022. p. 27-38. |
|
Idioma: |
Inglês |
|
Notas: |
GEOINFO 2022. |
|
Conteúdo: |
ABSTRACT - Brazilian agricultural production presents a high degree of spatial diversity, which challenges designing territorial public policies to promote sustainable development. This article proposes a new approach to cluster Brazilian municipalities according to their agricultural production. It combines a feature extraction mechanism using Deep Learning based on Autoencoders and clustering based on k-means and Self-Organizing Maps. We used the panel data from IBGE?s annual estimates of Brazilian agricultural production between 1999 and 2018. Different structures of simple stacked undercomplete autoencoders were analyzed, varying the number of layers and neurons in each of them, including the latent layer. We evaluated the asymmetric exponential linear loss function to cope with the sparse data. The results show that in comparison with the ground truth adopted, the autoencoder model combined with the Self-Organizing Maps and the k-means algorithm presented a better result than the clustering of the raw data from the k-means, demonstrating the ability of simple stacked autoencoders to reduce the dimensionality and create a new space of features in their latent layer where the data can be analyzed and clustered. Although the general accuracy is low, the results are promising, considering that we can add new improvements to the Deep Clustering process. |
|
Palavras-Chave: |
Clustering process. |
|
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
|
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1150828/1/6082.pdf
|
|
Marc: |
LEADER 02062nam a2200181 a 4500
001 2150828
005 2023-01-10
008 2022 bl uuuu u00u1 u #d
100 1 $aSILVA, M. A. S. da
245 $aFeature extraction of spatial panel data with autoencoders for clustering the Brazilian agricultural diversity.$h[electronic resource]
260 $aIn: BRAZILIAN SYMPOSIUM ON GEOINFORMATICS, 22., 2022, São José dos Campos. Proceedings... São José dos Campos: MCTIC/INPE, 2022. p. 27-38.$c2022
500 $aGEOINFO 2022.
520 $aABSTRACT - Brazilian agricultural production presents a high degree of spatial diversity, which challenges designing territorial public policies to promote sustainable development. This article proposes a new approach to cluster Brazilian municipalities according to their agricultural production. It combines a feature extraction mechanism using Deep Learning based on Autoencoders and clustering based on k-means and Self-Organizing Maps. We used the panel data from IBGE?s annual estimates of Brazilian agricultural production between 1999 and 2018. Different structures of simple stacked undercomplete autoencoders were analyzed, varying the number of layers and neurons in each of them, including the latent layer. We evaluated the asymmetric exponential linear loss function to cope with the sparse data. The results show that in comparison with the ground truth adopted, the autoencoder model combined with the Self-Organizing Maps and the k-means algorithm presented a better result than the clustering of the raw data from the k-means, demonstrating the ability of simple stacked autoencoders to reduce the dimensionality and create a new space of features in their latent layer where the data can be analyzed and clustered. Although the general accuracy is low, the results are promising, considering that we can add new improvements to the Deep Clustering process.
653 $aClustering process
700 1 $aMATOS, L. N.
700 1 $aSANTOS, F. E. DE O.
700 1 $aDOMPIERI, M. H. G.
700 1 $aMOURA, F. R. DE
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Territorial (CNPM) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Nenhum registro encontrado para a expressão de busca informada. |
|
|
