Matches in SemOpenAlex for { <https://semopenalex.org/work/W2132656721> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2132656721 abstract "Supervised learning methods such as Maximum Likeli- hood (ML) are often used in land cover (thematic) clas- sification of remote sensing imagery. ML classifier relies exclusively on spectral characteristics of thematic classes whose statistical distributions are often overlapping. The spectral response distributions of thematic classes are de- pendent on many factors including elevation, soil types, and atmospheric conditions present at the time of data acqui- sition. A second problem with statistical classifiers is the requirement of large number of accurate training samples, which are often costly and time consuming to acquire over large geographic regions. With the increasing availability of geospatial databases, it is possible to exploit the knowl- edge derived from these ancillary datasets to improve clas- sification accuracies even when the class distributions are highly overlapping. Likewise newer semi-supervised tech- niques can be adopted to improve the parameter estimates of statistical model by utilizing a large number of easily available unlabeled training samples. Unfortunately there is no convenient multivariate statistical model that can be employed for mulitsource geospatial databases. In this pa- per we present a hybrid semi-supervised learning algorithm that effectively exploits freely available unlabeled training samples from multispectral remote sensing images and also incorporates ancillary geospatial databases. We have con- ducted several experiments on real datasets, and our new hybrid approach shows over 15% improvement in classif- ciation accuracy over conventional classification schemes. Key Words: MLC, EM, Semi-supervised Learning." @default.
- W2132656721 created "2016-06-24" @default.
- W2132656721 creator A5029060972 @default.
- W2132656721 creator A5089170562 @default.
- W2132656721 creator A5090913753 @default.
- W2132656721 date "2007-10-01" @default.
- W2132656721 modified "2023-10-16" @default.
- W2132656721 title "A Hybrid Classification Scheme for Mining Multisource Geospatial Data" @default.
- W2132656721 cites W123339444 @default.
- W2132656721 cites W129457532 @default.
- W2132656721 cites W1535842702 @default.
- W2132656721 cites W1537967768 @default.
- W2132656721 cites W1563601573 @default.
- W2132656721 cites W1570448133 @default.
- W2132656721 cites W1587926959 @default.
- W2132656721 cites W1605695115 @default.
- W2132656721 cites W1840884391 @default.
- W2132656721 cites W1965895350 @default.
- W2132656721 cites W1993452522 @default.
- W2132656721 cites W2002645541 @default.
- W2132656721 cites W2034841618 @default.
- W2132656721 cites W2036255459 @default.
- W2132656721 cites W2039609561 @default.
- W2132656721 cites W2084502283 @default.
- W2132656721 cites W2097089247 @default.
- W2132656721 cites W2114968414 @default.
- W2132656721 cites W2122780641 @default.
- W2132656721 cites W2140187489 @default.
- W2132656721 cites W2911964244 @default.
- W2132656721 cites W2979832949 @default.
- W2132656721 cites W41502859 @default.
- W2132656721 cites W85350352 @default.
- W2132656721 doi "https://doi.org/10.1109/icdmw.2007.96" @default.
- W2132656721 hasPublicationYear "2007" @default.
- W2132656721 type Work @default.
- W2132656721 sameAs 2132656721 @default.
- W2132656721 citedByCount "12" @default.
- W2132656721 countsByYear W21326567212013 @default.
- W2132656721 countsByYear W21326567212014 @default.
- W2132656721 crossrefType "proceedings-article" @default.
- W2132656721 hasAuthorship W2132656721A5029060972 @default.
- W2132656721 hasAuthorship W2132656721A5089170562 @default.
- W2132656721 hasAuthorship W2132656721A5090913753 @default.
- W2132656721 hasConcept C119857082 @default.
- W2132656721 hasConcept C124101348 @default.
- W2132656721 hasConcept C153180895 @default.
- W2132656721 hasConcept C154945302 @default.
- W2132656721 hasConcept C165696696 @default.
- W2132656721 hasConcept C173163844 @default.
- W2132656721 hasConcept C205649164 @default.
- W2132656721 hasConcept C38652104 @default.
- W2132656721 hasConcept C41008148 @default.
- W2132656721 hasConcept C58640448 @default.
- W2132656721 hasConcept C62649853 @default.
- W2132656721 hasConcept C93692415 @default.
- W2132656721 hasConcept C95623464 @default.
- W2132656721 hasConcept C9770341 @default.
- W2132656721 hasConceptScore W2132656721C119857082 @default.
- W2132656721 hasConceptScore W2132656721C124101348 @default.
- W2132656721 hasConceptScore W2132656721C153180895 @default.
- W2132656721 hasConceptScore W2132656721C154945302 @default.
- W2132656721 hasConceptScore W2132656721C165696696 @default.
- W2132656721 hasConceptScore W2132656721C173163844 @default.
- W2132656721 hasConceptScore W2132656721C205649164 @default.
- W2132656721 hasConceptScore W2132656721C38652104 @default.
- W2132656721 hasConceptScore W2132656721C41008148 @default.
- W2132656721 hasConceptScore W2132656721C58640448 @default.
- W2132656721 hasConceptScore W2132656721C62649853 @default.
- W2132656721 hasConceptScore W2132656721C93692415 @default.
- W2132656721 hasConceptScore W2132656721C95623464 @default.
- W2132656721 hasConceptScore W2132656721C9770341 @default.
- W2132656721 hasLocation W21326567211 @default.
- W2132656721 hasOpenAccess W2132656721 @default.
- W2132656721 hasPrimaryLocation W21326567211 @default.
- W2132656721 hasRelatedWork W1497317973 @default.
- W2132656721 hasRelatedWork W1966028303 @default.
- W2132656721 hasRelatedWork W2001652754 @default.
- W2132656721 hasRelatedWork W2038239114 @default.
- W2132656721 hasRelatedWork W2148316240 @default.
- W2132656721 hasRelatedWork W2549006548 @default.
- W2132656721 hasRelatedWork W2807311372 @default.
- W2132656721 hasRelatedWork W2961085424 @default.
- W2132656721 hasRelatedWork W4214932115 @default.
- W2132656721 hasRelatedWork W3158004940 @default.
- W2132656721 isParatext "false" @default.
- W2132656721 isRetracted "false" @default.
- W2132656721 magId "2132656721" @default.
- W2132656721 workType "article" @default.