FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2317602876> ?p ?o ?g. }

• W2317602876 endingPage "2639" @default.
• W2317602876 startingPage "2627" @default.
• W2317602876 abstract "Recent classification-oriented proposals to thematic maps building from hyperspectral images have used both semisupervised approaches and spatial information for correction of spectral classification. Semisupervised approaches enrich the training data set adding similar samples to each class, whereas spatial correction is based on the natural assumption of thematic class spatial compactness. In this paper, we propose and validate the following innovations: 1) a new spectral classifier, which is called anticipative hybrid extreme rotation forest (AHERF); 2) a spatial-spectral semisupervised approach; and 3) a final spatial classification correction step. The novel heterogeneous ensemble learning approach AHERF starts with a model selection phase, using a small subsample of the training data, in order to define a ranking-based selection probability distribution of the classifier architectures that will be used in the ensemble, so that the architecture best adapted to the data domain will be used more frequently to train individual classifiers in the ensemble. After this initial phase, AHERF trains a heterogeneous ensemble applying random rotations to bootstrapped samples of the remaining training data, aiming to obtain diversified and data-domain adapted individual classifiers. The natural assumption that spatially close pixels will most likely have highly correlated values is exploited in two phases of the process pipeline. First, semisupervised label assignment is supported by spectral similarity and spatial proximity. Unsupervised spectral similarity is detected by latent class discovery. In this paper, we use a clustering algorithm (i.e., k-means). Second, maximizing class spatial compactness removes classification errors that appear as speckle noise in the classification image. The whole approach aims to use minimal sets of labeled pixels for training, which we call the seed training data set. Testing results are computed over the entire image ground truth. For comparison, we provide results in several steps: 1) of classification by AHERF and competing classifiers built by semisupervised training and 2) after spatial correction. We validate the approach on several conventional benchmarking images, achieving results which are comparable with state-of-the-art approaches." @default.
• W2317602876 created "2016-06-24" @default.
• W2317602876 creator A5064363543 @default.
• W2317602876 creator A5074974522 @default.
• W2317602876 date "2016-05-01" @default.
• W2317602876 modified "2023-09-25" @default.
• W2317602876 title "Hyperspectral Image Analysis by Spectral–Spatial Processing and Anticipative Hybrid Extreme Rotation Forest Classification" @default.
• W2317602876 cites W1968589019 @default.
• W2317602876 cites W1971176377 @default.
• W2317602876 cites W1974790686 @default.
• W2317602876 cites W1976935203 @default.
• W2317602876 cites W1982356933 @default.
• W2317602876 cites W1984232434 @default.
• W2317602876 cites W1991259147 @default.
• W2317602876 cites W1997718749 @default.
• W2317602876 cites W2001298023 @default.
• W2317602876 cites W2001859769 @default.
• W2317602876 cites W2002392274 @default.
• W2317602876 cites W2008847349 @default.
• W2317602876 cites W2012514949 @default.
• W2317602876 cites W2014555541 @default.
• W2317602876 cites W2016860790 @default.
• W2317602876 cites W2022788720 @default.
• W2317602876 cites W2031380708 @default.
• W2317602876 cites W2039609561 @default.
• W2317602876 cites W2041100636 @default.
• W2317602876 cites W2043665634 @default.
• W2317602876 cites W2043913960 @default.
• W2317602876 cites W2044283259 @default.
• W2317602876 cites W2045900692 @default.
• W2317602876 cites W2053615857 @default.
• W2317602876 cites W2053852479 @default.
• W2317602876 cites W2064604707 @default.
• W2317602876 cites W2076576187 @default.
• W2317602876 cites W2076656703 @default.
• W2317602876 cites W2077792904 @default.
• W2317602876 cites W2083069701 @default.
• W2317602876 cites W2086409142 @default.
• W2317602876 cites W2087263574 @default.
• W2317602876 cites W2093596219 @default.
• W2317602876 cites W2093679105 @default.
• W2317602876 cites W2096553553 @default.
• W2317602876 cites W2096673829 @default.
• W2317602876 cites W2098057602 @default.
• W2317602876 cites W2101711129 @default.
• W2317602876 cites W2103094532 @default.
• W2317602876 cites W2105386417 @default.
• W2317602876 cites W2106092565 @default.
• W2317602876 cites W2106277226 @default.
• W2317602876 cites W2107966405 @default.
• W2317602876 cites W2108917905 @default.
• W2317602876 cites W2112589365 @default.
• W2317602876 cites W2113464037 @default.
• W2317602876 cites W2114866007 @default.
• W2317602876 cites W2126517171 @default.
• W2317602876 cites W2127348003 @default.
• W2317602876 cites W2127612938 @default.
• W2317602876 cites W2131450755 @default.
• W2317602876 cites W2131697388 @default.
• W2317602876 cites W2131864940 @default.
• W2317602876 cites W2134317247 @default.
• W2317602876 cites W2139987077 @default.
• W2317602876 cites W2142012908 @default.
• W2317602876 cites W2145862305 @default.
• W2317602876 cites W2148791530 @default.
• W2317602876 cites W2149471024 @default.
• W2317602876 cites W2151056738 @default.
• W2317602876 cites W2159070926 @default.
• W2317602876 cites W2163491671 @default.
• W2317602876 cites W2163886442 @default.
• W2317602876 cites W2164437025 @default.
• W2317602876 cites W2165379615 @default.
• W2317602876 cites W2168867644 @default.
• W2317602876 cites W2171566342 @default.
• W2317602876 cites W2303501228 @default.
• W2317602876 cites W2478493250 @default.
• W2317602876 cites W4300989607 @default.
• W2317602876 cites W2102833157 @default.
• W2317602876 doi "https://doi.org/10.1109/tgrs.2015.2503886" @default.
• W2317602876 hasPublicationYear "2016" @default.
• W2317602876 type Work @default.
• W2317602876 sameAs 2317602876 @default.
• W2317602876 citedByCount "25" @default.
• W2317602876 countsByYear W23176028762017 @default.
• W2317602876 countsByYear W23176028762018 @default.
• W2317602876 countsByYear W23176028762019 @default.
• W2317602876 countsByYear W23176028762020 @default.
• W2317602876 countsByYear W23176028762021 @default.
• W2317602876 countsByYear W23176028762022 @default.
• W2317602876 countsByYear W23176028762023 @default.
• W2317602876 crossrefType "journal-article" @default.
• W2317602876 hasAuthorship W2317602876A5064363543 @default.
• W2317602876 hasAuthorship W2317602876A5074974522 @default.
• W2317602876 hasConcept C105795698 @default.
• W2317602876 hasConcept C115961682 @default.
• W2317602876 hasConcept C153180895 @default.
• W2317602876 hasConcept C154945302 @default.
• W2317602876 hasConcept C159078339 @default.

• next