Matches in SemOpenAlex for { <https://semopenalex.org/work/W2078264890> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2078264890 endingPage "1392" @default.
- W2078264890 startingPage "1385" @default.
- W2078264890 abstract "Multi-source data, either from different sensors or disparate features extracted from the same sensor, are valuable for geospatial image analysis due to their potential for providing complementary features. In this paper, a composite-kernel-based feature extraction method is proposed for multi-source remote sensing data classification. Features from different sources are first fused via a weighted composite kernel mapping, and then projected to a lower-dimensional subspace in which kernel local Fisher discriminant analysis (KLFDA) is used to extract the most discriminative information. We hypothesize that after such a projection, multi-source data would have better class separability between classes, and an efficient linear classification model–multinomial logistic regression (MLR) would be suitable for classification. The efficacy of the proposed method is demonstrated via experiments using two different sets of multi-source geospatial data. For feature fusion, the raw spectral data and extended multi-attribute profiles (EMAPs) derived from the hyperspectral image are used as a testbed for multi-source image analysis. The second multi-source testbed used for validation involves sensor fusion, in which the hyperspectral and light detection and ranging (LiDAR) data are utilized. Experimental results show that composite kernel local Fisher’s discriminant analysis when combined with MLR based classifier (CKLFDA-MLR) is very effective at feature extraction and classification of multi-source geospatial images." @default.
- W2078264890 created "2016-06-24" @default.
- W2078264890 creator A5002688054 @default.
- W2078264890 creator A5037823063 @default.
- W2078264890 date "2015-03-01" @default.
- W2078264890 modified "2023-09-29" @default.
- W2078264890 title "Locality Preserving Composite Kernel Feature Extraction for Multi-Source Geospatial Image Analysis" @default.
- W2078264890 cites W1978625957 @default.
- W2078264890 cites W2001150117 @default.
- W2078264890 cites W2029691617 @default.
- W2078264890 cites W2063385051 @default.
- W2078264890 cites W2067532478 @default.
- W2078264890 cites W2083522613 @default.
- W2078264890 cites W2127199143 @default.
- W2078264890 cites W2137933418 @default.
- W2078264890 cites W2140996489 @default.
- W2078264890 cites W2142387771 @default.
- W2078264890 cites W2149324654 @default.
- W2078264890 cites W2150579376 @default.
- W2078264890 cites W2151288205 @default.
- W2078264890 cites W2159070926 @default.
- W2078264890 cites W2164330327 @default.
- W2078264890 cites W2165796970 @default.
- W2078264890 doi "https://doi.org/10.1109/jstars.2014.2348537" @default.
- W2078264890 hasPublicationYear "2015" @default.
- W2078264890 type Work @default.
- W2078264890 sameAs 2078264890 @default.
- W2078264890 citedByCount "27" @default.
- W2078264890 countsByYear W20782648902015 @default.
- W2078264890 countsByYear W20782648902016 @default.
- W2078264890 countsByYear W20782648902017 @default.
- W2078264890 countsByYear W20782648902018 @default.
- W2078264890 countsByYear W20782648902019 @default.
- W2078264890 countsByYear W20782648902020 @default.
- W2078264890 countsByYear W20782648902021 @default.
- W2078264890 crossrefType "journal-article" @default.
- W2078264890 hasAuthorship W2078264890A5002688054 @default.
- W2078264890 hasAuthorship W2078264890A5037823063 @default.
- W2078264890 hasConcept C114614502 @default.
- W2078264890 hasConcept C127313418 @default.
- W2078264890 hasConcept C138885662 @default.
- W2078264890 hasConcept C153180895 @default.
- W2078264890 hasConcept C154945302 @default.
- W2078264890 hasConcept C2776401178 @default.
- W2078264890 hasConcept C2779808786 @default.
- W2078264890 hasConcept C33923547 @default.
- W2078264890 hasConcept C41008148 @default.
- W2078264890 hasConcept C41895202 @default.
- W2078264890 hasConcept C52622490 @default.
- W2078264890 hasConcept C62649853 @default.
- W2078264890 hasConcept C74193536 @default.
- W2078264890 hasConcept C9770341 @default.
- W2078264890 hasConceptScore W2078264890C114614502 @default.
- W2078264890 hasConceptScore W2078264890C127313418 @default.
- W2078264890 hasConceptScore W2078264890C138885662 @default.
- W2078264890 hasConceptScore W2078264890C153180895 @default.
- W2078264890 hasConceptScore W2078264890C154945302 @default.
- W2078264890 hasConceptScore W2078264890C2776401178 @default.
- W2078264890 hasConceptScore W2078264890C2779808786 @default.
- W2078264890 hasConceptScore W2078264890C33923547 @default.
- W2078264890 hasConceptScore W2078264890C41008148 @default.
- W2078264890 hasConceptScore W2078264890C41895202 @default.
- W2078264890 hasConceptScore W2078264890C52622490 @default.
- W2078264890 hasConceptScore W2078264890C62649853 @default.
- W2078264890 hasConceptScore W2078264890C74193536 @default.
- W2078264890 hasConceptScore W2078264890C9770341 @default.
- W2078264890 hasFunder F4320306101 @default.
- W2078264890 hasIssue "3" @default.
- W2078264890 hasLocation W20782648901 @default.
- W2078264890 hasOpenAccess W2078264890 @default.
- W2078264890 hasPrimaryLocation W20782648901 @default.
- W2078264890 hasRelatedWork W2003939146 @default.
- W2078264890 hasRelatedWork W2016461833 @default.
- W2078264890 hasRelatedWork W2104912729 @default.
- W2078264890 hasRelatedWork W2110459882 @default.
- W2078264890 hasRelatedWork W2144059113 @default.
- W2078264890 hasRelatedWork W2146076056 @default.
- W2078264890 hasRelatedWork W2151022383 @default.
- W2078264890 hasRelatedWork W2382607599 @default.
- W2078264890 hasRelatedWork W2811390910 @default.
- W2078264890 hasRelatedWork W3197541072 @default.
- W2078264890 hasVolume "8" @default.
- W2078264890 isParatext "false" @default.
- W2078264890 isRetracted "false" @default.
- W2078264890 magId "2078264890" @default.
- W2078264890 workType "article" @default.