@InProceedings{Martins-BedêReiPanDutSan:2014:ApMuSp,
               author = "Martins-Bed{\^e}, Fl{\'a}via de Toledo and Reis, Mariane Souza 
                         and Pantale{\~a}o, Eliana and Dutra, Luciano Vieira and Sandri, 
                         Sandra Aparecida",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de 
                         Pesquisas Espaciais (INPE)}",
                title = "An application of multiple space nearest neighbor classifier in 
                         land cover classification",
            booktitle = "Proceedings...",
                 year = "2014",
                pages = "1713--17",
         organization = "IEEE International Geoscience and Remote Sensing Symposium, 
                         (IGARSS 2014).",
            publisher = "IEEE",
                 note = "{Setores de Atividade: Impress{\~a}o e reprodu{\c{c}}{\~a}o de 
                         grava{\c{c}}{\~o}es.}",
             keywords = "land cover classification, multiple space nearest neighbor, 
                         classification algorithm, SAR and optical data classification.",
             abstract = "This work presents a case study in land cover classification using 
                         ms-NN, an extension of k-NN classification algorithm. The case 
                         study focuses on an area in the Brazilian Amazon region, with data 
                         obtained from LANDSAT5 satellite Thematic Mapper (TM) sensor and 
                         Advanced Land Observing System satellite (ALOS) Phase Array L-Band 
                         Synthetic Aperture Radar (PALSAR), using Fine Beam Dual. The 
                         results obtained with ms-NN are compared with k-NN and Support 
                         Vector Machine algorithms, considering the use of a single 
                         training set, a Monte Carlo procedure for testing and an extensive 
                         number of parameterizations for the classification methods. 
                         Considering only the best results for each classifier, ms-NN 
                         obtained better results than the other methods.",
  conference-location = "Quebec City",
      conference-year = "2014",
                  doi = "10.1109/IGARSS.2014.6946781",
                  url = "http://dx.doi.org/10.1109/IGARSS.2014.6946781",
                 isbn = "9781479957750",
                label = "lattes: 9840759640842299 4 
                         ToledoMartins-BedeReiPanDutSan:2014:ApMuSp",
             language = "pt",
           targetfile = "06946781flavia.pdf",
                  url = "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=\&arnumber=6946781\&refinements%3D4294967269%2C4291944822%2C4291944246%2C4291944245%26ranges%3D2013_2015_p_Publication_Year%26matchBoolean%3Dtrue%26searchField%3DSearch_All%26queryText%3D%28p_Authors",
        urlaccessdate = "19 abr. 2024"
}