| 1. Identity statement | |
| Reference Type | Journal Article |
| Site | plutao.sid.inpe.br |
| Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
| Identifier | 8JMKD3MGP3W/3FCLSSE |
| Repository | sid.inpe.br/plutao/2013/12.12.19.59 |
| Last Update | 2015:03.13.18.16.14 (UTC) administrator |
| Metadata Repository | sid.inpe.br/plutao/2013/12.12.19.59.01 |
| Metadata Last Update | 2018:06.04.23.39.26 (UTC) administrator |
| ISSN | 0560-4613 1808-0936 |
| Label | lattes: 0063119667740811 3 NascimentoAlcâKampStec:2013:CASTTR |
| Citation Key | NascimentoAlcâKampStec:2013:CaStTr |
| Title | An assessment of the support vector machine for a CBES-2 CCD image classification: a case study of a tropical reservoir in brazil  |
| Year | 2013 |
| Access Date | 2024, May 19 |
| Type of Work | journal article |
| Secondary Type | PRE PN |
| Number of Files | 1 |
| Size | 665 KiB |
| 2. Context | |
| Author | 1 Nascimento, Renata 2 Alcântara, Enner Herenio de 3 Kampel, Milton 4 Stech, José Luiz |
| Resume Identifier | 1 2 3 8JMKD3MGP5W/3C9JHTG 4 8JMKD3MGP5W/3C9JHHN |
| Group | 1 DSR-OBT-INPE-MCTI-GOV-BR 2 3 DSR-OBT-INPE-MCTI-GOV-BR 4 DSR-OBT-INPE-MCTI-GOV-BR |
| Affiliation | 1 Instituto Nacional de Pesquisas Espaciais (INPE) 2 Universidade Estadual Paulista (UNESP) 3 Instituto Nacional de Pesquisas Espaciais (INPE) 4 Instituto Nacional de Pesquisas Espaciais (INPE) |
| Author e-Mail Address | 1 re_ffnascimento@yahoo.com.br 2 enner@pq.cnpq.br 3 milton@dsr.inpe.br 4 stech@ltid.inpe.br |
| e-Mail Address | milton@dsr.inpe.br |
| Journal | Revista Brasileira de Cartografia |
| Volume | 65 |
| Number | 3 |
| Pages | 431-439 |
| History (UTC) | 2013-12-12 19:59:01 :: lattes -> administrator :: 2018-06-04 23:39:26 :: administrator -> marcelo.pazos@inpe.br :: 2013 |
| 3. Content and structure | |
| Is the master or a copy? | is the master |
| Content Stage | completed |
| Transferable | 1 |
| Content Type | External Contribution |
| Version Type | publisher |
| Keywords | Tropical reservoir CBERS Support vector machine |
| Abstract | The support vector machine (SVM) is a group of theoretically superior machine learning algorithms and has recently become an effective tool for pattern recognition. The aim of this work was to compare this newer classification algorithm against a traditional statistical classifier and to assess their accuracy. The area surrounding the Itumbiara reservoir in the State of Goiás, Brazil was selected as the study area. The classes were defined in accordance with the Cover Classification System of the Food and Agriculture Organization of the United Nations (FAO). Training sets were collected for each class, and the algorithms were then applied. A confusion matrix and Kappa coefficients were used to evaluate the classification algorithm. The computed accuracy was approximately 71%, and the Kappa coefficient was 0.64 for the SVM classification. For the maximum likelihood (ML) the overall accuracy was 49% and the Kappa coefficient was 0.36. According to these results, the optimal class separation by the SVM algorithm was considered to be appreciably better than the ML classification. RESUMO: O Máquina de Suporte Vetorial (MSV) é um grupo teórico de algoritmos de aprendizagem de máquina e recentemente se tornou uma ferramenta efetiva para o reconhecimento de padrões. O objetivo deste trabalho foi o de comparar esse novo classificador contra os classificadores estatísticos tradicionais e avaliar sua acurácia. A área selecionada para realizar esse experimento foi a área de influência do reservatório hidrelétrico de Itumbiara (GO). As classes selecionadas foram obtidas pelo sistema de classificação de cobertura da FAO. Amostras de treinamento foram coletadas para cada classe e os algoritmos de classificação foram então aplicados. O coeficiente Kappa foi utilizado para avaliar os classificadores. Os resultados mostraram que para o algoritmo MSV a acurácia foi de 71% com um coeficiente Kappa de 0,64. Para o algoritmo de máxima verossimilhança a acurácia foi de 49% com Kappa de 0,36. De acordo com esses resultados, para a classificação da área de estudo selecionada, o algoritmo MSV apresentou melhor resultado na separação das classes propostas pela FAO. |
| Area | SRE |
| Arrangement | urlib.net > BDMCI > Fonds > Produção anterior à 2021 > DIDSR > An assessment of... |
| doc Directory Content | access |
| source Directory Content | there are no files |
| agreement Directory Content | there are no files |
| 4. Conditions of access and use | |
| data URL | http://urlib.net/ibi/8JMKD3MGP3W/3FCLSSE |
| zipped data URL | http://urlib.net/zip/8JMKD3MGP3W/3FCLSSE |
| Language | en |
| User Group | lattes marcelo.pazos@inpe.br |
| Reader Group | administrator marcelo.pazos@inpe.br |
| Visibility | shown |
| Archiving Policy | allowpublisher allowfinaldraft |
| Read Permission | allow from all |
| Update Permission | not transferred |
| 5. Allied materials | |
| Mirror Repository | iconet.com.br/banon/2006/11.26.21.31 |
| Next Higher Units | 8JMKD3MGPCW/3ER446E |
| Citing Item List | sid.inpe.br/mtc-m21/2012/07.13.14.56.38 1 |
| URL (untrusted data) | http://www.lsie.unb.br/rbc/index.php/rbc/article/view/600 |
| Dissemination | PORTALCAPES |
| Host Collection | dpi.inpe.br/plutao@80/2008/08.19.15.01 |
| 6. Notes | |
| Empty Fields | alternatejournal archivist callnumber copyholder copyright creatorhistory descriptionlevel doi format isbn lineage mark month nextedition notes orcid parameterlist parentrepositories previousedition previouslowerunit progress project rightsholder schedulinginformation secondarydate secondarykey secondarymark session shorttitle sponsor subject targetfile tertiarymark tertiarytype |
| 7. Description control | |
| e-Mail (login) | marcelo.pazos@inpe.br |
| update | |