FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2742777231> ?p ?o ?g. }

• W2742777231 abstract "Data acquired from multi-channel sensors is a highly valuable asset to interpret the environment for a variety of remote sensing applications. However, low spatial resolution is a critical limitation for previous sensors and the constituent materials of a scene can be mixed in different fractions due to their spatial interactions. Spectral unmixing is a technique that allows us to obtain the material spectral signatures and their fractions from hyperspectral data. In this paper, we propose a novel endmember extraction and hyperspectral unmixing scheme, so called textit{EndNet}, that is based on a two-staged autoencoder network. This well-known structure is completely enhanced and restructured by introducing additional layers and a projection metric (i.e., spectral angle distance (SAD) instead of inner product) to achieve an optimum solution. Moreover, we present a novel loss function that is composed of a Kullback-Leibler divergence term with SAD similarity and additional penalty terms to improve the sparsity of the estimates. These modifications enable us to set the common properties of endmembers such as non-linearity and sparsity for autoencoder networks. Lastly, due to the stochastic-gradient based approach, the method is scalable for large-scale data and it can be accelerated on Graphical Processing Units (GPUs). To demonstrate the superiority of our proposed method, we conduct extensive experiments on several well-known datasets. The results confirm that the proposed method considerably improves the performance compared to the state-of-the-art techniques in literature." @default.
• W2742777231 created "2017-08-17" @default.
• W2742777231 creator A5009437653 @default.
• W2742777231 creator A5058810174 @default.
• W2742777231 creator A5076424815 @default.
• W2742777231 date "2017-08-06" @default.
• W2742777231 modified "2023-09-24" @default.
• W2742777231 title "EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing" @default.
• W2742777231 cites W114517082 @default.
• W2742777231 cites W1181348626 @default.
• W2742777231 cites W1508246414 @default.
• W2742777231 cites W1522301498 @default.
• W2742777231 cites W1677182931 @default.
• W2742777231 cites W1836465849 @default.
• W2742777231 cites W1853900790 @default.
• W2742777231 cites W1902016676 @default.
• W2742777231 cites W1921523184 @default.
• W2742777231 cites W1957094454 @default.
• W2742777231 cites W1981939910 @default.
• W2742777231 cites W2003896345 @default.
• W2742777231 cites W2008924446 @default.
• W2742777231 cites W2009576740 @default.
• W2742777231 cites W2011315899 @default.
• W2742777231 cites W2027878671 @default.
• W2742777231 cites W2028469338 @default.
• W2742777231 cites W2033178790 @default.
• W2742777231 cites W2042626896 @default.
• W2742777231 cites W2042737021 @default.
• W2742777231 cites W2053186076 @default.
• W2742777231 cites W2061280223 @default.
• W2742777231 cites W2076332129 @default.
• W2742777231 cites W2081867871 @default.
• W2742777231 cites W2089666662 @default.
• W2742777231 cites W2095705004 @default.
• W2742777231 cites W2097153652 @default.
• W2742777231 cites W2101837437 @default.
• W2742777231 cites W2105002599 @default.
• W2742777231 cites W2109006918 @default.
• W2742777231 cites W2113753426 @default.
• W2742777231 cites W2114486983 @default.
• W2742777231 cites W2117027921 @default.
• W2742777231 cites W2125298866 @default.
• W2742777231 cites W2128873066 @default.
• W2742777231 cites W2133782497 @default.
• W2742777231 cites W2139047226 @default.
• W2742777231 cites W2145094598 @default.
• W2742777231 cites W2152722485 @default.
• W2742777231 cites W2156316030 @default.
• W2742777231 cites W2156458885 @default.
• W2742777231 cites W2156517622 @default.
• W2742777231 cites W2157321686 @default.
• W2742777231 cites W2159874418 @default.
• W2742777231 cites W2163202748 @default.
• W2742777231 cites W2163886442 @default.
• W2742777231 cites W2163922914 @default.
• W2742777231 cites W2167244571 @default.
• W2742777231 cites W2169924573 @default.
• W2742777231 cites W2170395949 @default.
• W2742777231 cites W2171490498 @default.
• W2742777231 cites W2172063876 @default.
• W2742777231 cites W2176412452 @default.
• W2742777231 cites W2187089797 @default.
• W2742777231 cites W2218318129 @default.
• W2742777231 cites W2239643428 @default.
• W2742777231 cites W2428361224 @default.
• W2742777231 cites W2502312327 @default.
• W2742777231 cites W2517982728 @default.
• W2742777231 cites W2610928256 @default.
• W2742777231 cites W2765455392 @default.
• W2742777231 cites W2771346875 @default.
• W2742777231 cites W2951618017 @default.
• W2742777231 cites W3041868831 @default.
• W2742777231 cites W3122463936 @default.
• W2742777231 cites W830076066 @default.
• W2742777231 hasPublicationYear "2017" @default.
• W2742777231 type Work @default.
• W2742777231 sameAs 2742777231 @default.
• W2742777231 citedByCount "3" @default.
• W2742777231 countsByYear W27427772312018 @default.
• W2742777231 crossrefType "posted-content" @default.
• W2742777231 hasAuthorship W2742777231A5009437653 @default.
• W2742777231 hasAuthorship W2742777231A5058810174 @default.
• W2742777231 hasAuthorship W2742777231A5076424815 @default.
• W2742777231 hasConcept C101738243 @default.
• W2742777231 hasConcept C103278499 @default.
• W2742777231 hasConcept C11413529 @default.
• W2742777231 hasConcept C115961682 @default.
• W2742777231 hasConcept C138885662 @default.
• W2742777231 hasConcept C153180895 @default.
• W2742777231 hasConcept C154945302 @default.
• W2742777231 hasConcept C159078339 @default.
• W2742777231 hasConcept C162324750 @default.
• W2742777231 hasConcept C176217482 @default.
• W2742777231 hasConcept C207390915 @default.
• W2742777231 hasConcept C21547014 @default.
• W2742777231 hasConcept C41008148 @default.
• W2742777231 hasConcept C41895202 @default.
• W2742777231 hasConcept C50644808 @default.
• W2742777231 hasConcept C57493831 @default.
• W2742777231 hasConcept C58237817 @default.

• next