Close
Metadata

1. Identity statement
Reference TypeJournal Article
Sitemtc-m16d.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP7W/3B6G3JP
Repositorysid.inpe.br/mtc-m19/2012/01.10.12.26
Last Update2012:01.10.12.31.11 (UTC) administrator
Metadata Repositorysid.inpe.br/mtc-m19/2012/01.10.12.26.54
Metadata Last Update2018:06.05.04.35.40 (UTC) administrator
Secondary KeyINPE--PRE/
ISSN0560-4613
1808-0936
Citation KeySousaTeiSilAndBra:2010:AvClBa
TitleAvaliação de classificadores baseados em aprendizado de máquina para a classificação do uso e cobertura da terra no bioma caatinga
Year2010
Monthset.
Access Date2024, May 18
Secondary TypePRE PN
Number of Files1
Size671 KiB
2. Context
Author1 Sousa, Beatriz Fernandes Simplicio
2 Teixeira, Adunias dos Santos
3 Silva, Francisco de Assis Tavares Ferreira da
4 Andrade, Eunice Maia de
5 Braga, Arthur Plínio de Souza
Resume Identifier1
2
3 8JMKD3MGP5W/3C9JH4L
Group1
2
3 CRN-CCR-INPE-MCT-BR
Affiliation1
2
3 Instituto Nacional de Pesquisas Espaciais (INPE)
JournalRevista Brasileira de Cartografia
Volume62
Number2 , setembro 2010.
Pagesedição Especial
History (UTC)2012-01-10 12:33:04 :: marciana -> administrator :: 2010
2018-06-05 04:35:40 :: administrator -> marciana :: 2010
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Version Typepublisher
KeywordsInteligência Artificial
Semi-árido
Classificação de Imagens de Satélite
Artificial Intelligence
Semi Arid
Satellite Image Classification
AbstractO manejo adequado dos recursos naturais em ambientes frágeis, como o da Caatinga, requer o conhecimento de suas propriedades e distribuição espacial. Nesse contexto, o trabalho tem por objetivo avaliar o desempenho de dois algoritmos baseados em aprendizado de máquina (Multi Layer Perceptron (MLP) e o Support Vector Machine (SVM)) e do método da Máxima Verossimilhança na classificação do uso e cobertura da terra no bioma Caatinga. Para o experimento, foi utilizada uma imagem do satélite LANDSAT-5/TM contendo a área de estudo localizada no município de Iguatu-CE e definidas as classes de cobertura da terra, a saber: antropização por agricultura (APA), outros tipos de antropização (OTA), água, caatinga herbácea arbustiva (CHA) e caatinga arbórea densa (CAD). O desempenho dos métodos foi analisado através dos coeficientes de Exatidão Global (EG), Exatidão Específica (EE) e Kappa (K) calculados a partir dos dados da matriz de confusão correspondente à verdade terrestre. Os valores do coeficiente de EG foram de: 86,03%, 82,14% e 81,2% e K de: 0,77, 0,76 e 0,75 nos métodos SVM, MLP e Máxima Verossimilhança, respectivamente. Os valores de EE foram superiores a 70% para todos os classificadores testados. Os resultados obtidos demonstram que os métodos SVM e MLP estão aptos à classificação dos padrões propostos, já que apresentaram resultados semelhantes ao método tradicional da Máxima Verossimilhança. Porém, estes classificadores podem consumir mais tempo na etapa de definição dos parâmetros da rede e de processamento.ABSTRACT Proper management of natural resources in fragile environments, such as the Caatinga, requires knowledge of their properties and spatial distribution. In this context, the study aims at evaluating the performance of two algorithms based on machine learning (Multi Layer Perceptron (MLP) and Support Vector Machine (SVM)) and the Maximum Proper management of natural resources in fragile environments, such as the Caatinga, requires knowledge of their properties and spatial distribution. In this context, the study aims at evaluating the performance of two algorithms based on machine learning (Multi Layer Perceptron (MLP) and Support Vector Machine (SVM)) and the Maximum Likelihood method to classify land use and land cover in the Caatinga biome. For the experiment, it was used a satellite image of LANDSAT-5/TM containing the study area located in the municipality of Iguatu-CE, and classes of land cover, namely: anthropized by agriculture, other types of anthropized, water, herbaceous shrub savanna (CHA ) and dense arboreal savanna (CAD) were defined. The performance of the methods was analyzed by the coefficient of Global Accuracy (EG), Accuracy Specific (EE) and Kappa (K) coefficient calculated with data taken from the confusion matrix corresponding to ground truth. The coefficient of EG were: 86.03%, 82.14% and 81.2% and K: 0.77, 0.76 and 0.75 in the methods SVM, MLP and maximum likelihood respectively. EE values were above 70% for all classifiers tested. The results have shown that SVM and MLP methods are suited to the classification of the proposed standards, as it showed similar results to the traditional method of maximum likelihood. However, these methods are more time consuming in the stage of defining the parameters of the network and may require more computation power during stage of processing.
AreaSRE
Arrangementurlib.net > BDMCI > Fonds > Produção anterior à 2021 > CRCRN > Avaliação de classificadores...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 10/01/2012 10:26 1.0 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGP7W/3B6G3JP
zipped data URLhttp://urlib.net/zip/8JMKD3MGP7W/3B6G3JP
Languagept
Target File62_ESPECIAL_02_6.pdf
User Groupadministrator
marciana
Visibilityshown
Archiving Policyallowpublisher allowfinaldraft
Read Permissionallow from all
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/mtc-m19@80/2009/08.21.17.02.53
Next Higher Units8JMKD3MGPCW/3EUAPES
Citing Item Listsid.inpe.br/mtc-m21/2012/07.13.14.46.21 5
sid.inpe.br/bibdigital/2013/10.03.20.46 1
DisseminationPORTALCAPES
Host Collectionsid.inpe.br/mtc-m19@80/2009/08.21.17.02
6. Notes
Empty Fieldsalternatejournal archivist callnumber copyholder copyright creatorhistory descriptionlevel doi e-mailaddress electronicmailaddress format isbn label lineage mark nextedition notes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup rightsholder schedulinginformation secondarydate secondarymark session shorttitle sponsor subject tertiarymark tertiarytype typeofwork url
7. Description control
e-Mail (login)marciana
update 


Close