FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2150045166> ?p ?o ?g. }

• W2150045166 endingPage "2232" @default.
• W2150045166 startingPage "2218" @default.
• W2150045166 abstract "In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed." @default.
• W2150045166 created "2016-06-24" @default.
• W2150045166 creator A5005192117 @default.
• W2150045166 creator A5006062906 @default.
• W2150045166 creator A5021292760 @default.
• W2150045166 creator A5037162971 @default.
• W2150045166 creator A5068472081 @default.
• W2150045166 date "2009-07-01" @default.
• W2150045166 modified "2023-10-18" @default.
• W2150045166 title "Active Learning Methods for Remote Sensing Image Classification" @default.
• W2150045166 cites W1528361845 @default.
• W2150045166 cites W1537192798 @default.
• W2150045166 cites W1553262910 @default.
• W2150045166 cites W1965555277 @default.
• W2150045166 cites W1978633512 @default.
• W2150045166 cites W1988790447 @default.
• W2150045166 cites W1997903011 @default.
• W2150045166 cites W2013729812 @default.
• W2150045166 cites W2063546309 @default.
• W2150045166 cites W2065010255 @default.
• W2150045166 cites W2076131212 @default.
• W2150045166 cites W2078086156 @default.
• W2150045166 cites W2078619499 @default.
• W2150045166 cites W2080021732 @default.
• W2150045166 cites W2083515729 @default.
• W2150045166 cites W2087347434 @default.
• W2150045166 cites W2096334333 @default.
• W2150045166 cites W2097089247 @default.
• W2150045166 cites W2098203240 @default.
• W2150045166 cites W2098758111 @default.
• W2150045166 cites W2099129687 @default.
• W2150045166 cites W2101711129 @default.
• W2150045166 cites W2101927381 @default.
• W2150045166 cites W2102049927 @default.
• W2150045166 cites W2104269704 @default.
• W2150045166 cites W2115305054 @default.
• W2150045166 cites W2117897510 @default.
• W2150045166 cites W2124706543 @default.
• W2150045166 cites W2134663338 @default.
• W2150045166 cites W2136251662 @default.
• W2150045166 cites W2138849239 @default.
• W2150045166 cites W2148275879 @default.
• W2150045166 cites W2156316030 @default.
• W2150045166 cites W2168481151 @default.
• W2150045166 cites W2172177790 @default.
• W2150045166 cites W2487087946 @default.
• W2150045166 cites W2949071206 @default.
• W2150045166 cites W4230030242 @default.
• W2150045166 cites W4250800088 @default.
• W2150045166 doi "https://doi.org/10.1109/tgrs.2008.2010404" @default.
• W2150045166 hasPublicationYear "2009" @default.
• W2150045166 type Work @default.
• W2150045166 sameAs 2150045166 @default.
• W2150045166 citedByCount "424" @default.
• W2150045166 countsByYear W21500451662012 @default.
• W2150045166 countsByYear W21500451662013 @default.
• W2150045166 countsByYear W21500451662014 @default.
• W2150045166 countsByYear W21500451662015 @default.
• W2150045166 countsByYear W21500451662016 @default.
• W2150045166 countsByYear W21500451662017 @default.
• W2150045166 countsByYear W21500451662018 @default.
• W2150045166 countsByYear W21500451662019 @default.
• W2150045166 countsByYear W21500451662020 @default.
• W2150045166 countsByYear W21500451662021 @default.
• W2150045166 countsByYear W21500451662022 @default.
• W2150045166 countsByYear W21500451662023 @default.
• W2150045166 crossrefType "journal-article" @default.
• W2150045166 hasAuthorship W2150045166A5005192117 @default.
• W2150045166 hasAuthorship W2150045166A5006062906 @default.
• W2150045166 hasAuthorship W2150045166A5021292760 @default.
• W2150045166 hasAuthorship W2150045166A5037162971 @default.
• W2150045166 hasAuthorship W2150045166A5068472081 @default.
• W2150045166 hasConcept C111919701 @default.
• W2150045166 hasConcept C115961682 @default.
• W2150045166 hasConcept C119857082 @default.
• W2150045166 hasConcept C12267149 @default.
• W2150045166 hasConcept C127705205 @default.
• W2150045166 hasConcept C153180895 @default.
• W2150045166 hasConcept C154945302 @default.
• W2150045166 hasConcept C159078339 @default.
• W2150045166 hasConcept C160633673 @default.
• W2150045166 hasConcept C41008148 @default.
• W2150045166 hasConcept C75294576 @default.
• W2150045166 hasConcept C774472 @default.
• W2150045166 hasConcept C95623464 @default.
• W2150045166 hasConceptScore W2150045166C111919701 @default.
• W2150045166 hasConceptScore W2150045166C115961682 @default.
• W2150045166 hasConceptScore W2150045166C119857082 @default.
• W2150045166 hasConceptScore W2150045166C12267149 @default.
• W2150045166 hasConceptScore W2150045166C127705205 @default.
• W2150045166 hasConceptScore W2150045166C153180895 @default.
• W2150045166 hasConceptScore W2150045166C154945302 @default.
• W2150045166 hasConceptScore W2150045166C159078339 @default.
• W2150045166 hasConceptScore W2150045166C160633673 @default.
• W2150045166 hasConceptScore W2150045166C41008148 @default.
• W2150045166 hasConceptScore W2150045166C75294576 @default.
• W2150045166 hasConceptScore W2150045166C774472 @default.
• W2150045166 hasConceptScore W2150045166C95623464 @default.

• next