FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198416344> ?p ?o ?g. }

• W3198416344 endingPage "3412" @default.
• W3198416344 startingPage "3412" @default.
• W3198416344 abstract "By combining the broad learning and a convolutional neural network (CNN), a block-diagonal constrained multi-stage convolutional broad learning (MSCBL-BD) method is proposed for hyperspectral image (HSI) classification. Firstly, as the linear sparse feature extracted by the conventional broad learning method cannot fully characterize the complex spatial-spectral features of HSIs, we replace the linear sparse features in the mapped feature (MF) with the features extracted by the CNN to achieve more complex nonlinear mapping. Then, in the multi-layer mapping process of the CNN, information loss occurs to a certain degree. To this end, the multi-stage convolutional features (MSCFs) extracted by the CNN are expanded to obtain the multi-stage broad features (MSBFs). MSCFs and MSBFs are further spliced to obtain multi-stage convolutional broad features (MSCBFs). Additionally, in order to enhance the mutual independence between MSCBFs, a block diagonal constraint is introduced, and MSCBFs are mapped by a block diagonal matrix, so that each feature is represented linearly only by features of the same stage. Finally, the output layer weights of MSCBL-BD and the desired block-diagonal matrix are solved by the alternating direction method of multipliers. Experimental results on three popular HSI datasets demonstrate the superiority of MSCBL-BD." @default.
• W3198416344 created "2021-09-13" @default.
• W3198416344 creator A5000868256 @default.
• W3198416344 creator A5012528047 @default.
• W3198416344 creator A5017534600 @default.
• W3198416344 creator A5068039063 @default.
• W3198416344 date "2021-08-27" @default.
• W3198416344 modified "2023-10-16" @default.
• W3198416344 title "Multi-Stage Convolutional Broad Learning with Block Diagonal Constraint for Hyperspectral Image Classification" @default.
• W3198416344 cites W1997201895 @default.
• W3198416344 cites W2008233110 @default.
• W3198416344 cites W2012742472 @default.
• W3198416344 cites W2019338222 @default.
• W3198416344 cites W2022631295 @default.
• W3198416344 cites W2029316659 @default.
• W3198416344 cites W2041100636 @default.
• W3198416344 cites W2045786596 @default.
• W3198416344 cites W2087263574 @default.
• W3198416344 cites W2090424610 @default.
• W3198416344 cites W2103972604 @default.
• W3198416344 cites W2171171329 @default.
• W3198416344 cites W2179290474 @default.
• W3198416344 cites W2241001100 @default.
• W3198416344 cites W2242204034 @default.
• W3198416344 cites W2314785379 @default.
• W3198416344 cites W2331181944 @default.
• W3198416344 cites W2345128667 @default.
• W3198416344 cites W2412588858 @default.
• W3198416344 cites W2417947228 @default.
• W3198416344 cites W2494628060 @default.
• W3198416344 cites W2500751094 @default.
• W3198416344 cites W2516282711 @default.
• W3198416344 cites W2518815253 @default.
• W3198416344 cites W2527650001 @default.
• W3198416344 cites W2534411035 @default.
• W3198416344 cites W2545016534 @default.
• W3198416344 cites W2548791488 @default.
• W3198416344 cites W2558391528 @default.
• W3198416344 cites W2560523472 @default.
• W3198416344 cites W2561545456 @default.
• W3198416344 cites W2574404198 @default.
• W3198416344 cites W2587790406 @default.
• W3198416344 cites W2598997103 @default.
• W3198416344 cites W2603422184 @default.
• W3198416344 cites W2607476064 @default.
• W3198416344 cites W2611715706 @default.
• W3198416344 cites W2728364730 @default.
• W3198416344 cites W2738226240 @default.
• W3198416344 cites W2738447277 @default.
• W3198416344 cites W2754507318 @default.
• W3198416344 cites W2770495564 @default.
• W3198416344 cites W2782522152 @default.
• W3198416344 cites W2801275556 @default.
• W3198416344 cites W2801324747 @default.
• W3198416344 cites W2887576641 @default.
• W3198416344 cites W2890126432 @default.
• W3198416344 cites W2918703174 @default.
• W3198416344 cites W2919115771 @default.
• W3198416344 cites W2962702700 @default.
• W3198416344 cites W3102431071 @default.
• W3198416344 cites W3106090851 @default.
• W3198416344 doi "https://doi.org/10.3390/rs13173412" @default.
• W3198416344 hasPublicationYear "2021" @default.
• W3198416344 type Work @default.
• W3198416344 sameAs 3198416344 @default.
• W3198416344 citedByCount "2" @default.
• W3198416344 countsByYear W31984163442023 @default.
• W3198416344 crossrefType "journal-article" @default.
• W3198416344 hasAuthorship W3198416344A5000868256 @default.
• W3198416344 hasAuthorship W3198416344A5012528047 @default.
• W3198416344 hasAuthorship W3198416344A5017534600 @default.
• W3198416344 hasAuthorship W3198416344A5068039063 @default.
• W3198416344 hasBestOaLocation W31984163441 @default.
• W3198416344 hasConcept C11413529 @default.
• W3198416344 hasConcept C121332964 @default.
• W3198416344 hasConcept C130367717 @default.
• W3198416344 hasConcept C138885662 @default.
• W3198416344 hasConcept C153180895 @default.
• W3198416344 hasConcept C154945302 @default.
• W3198416344 hasConcept C158693339 @default.
• W3198416344 hasConcept C159078339 @default.
• W3198416344 hasConcept C2524010 @default.
• W3198416344 hasConcept C2776036281 @default.
• W3198416344 hasConcept C2776401178 @default.
• W3198416344 hasConcept C2777210771 @default.
• W3198416344 hasConcept C33923547 @default.
• W3198416344 hasConcept C41008148 @default.
• W3198416344 hasConcept C41895202 @default.
• W3198416344 hasConcept C62520636 @default.
• W3198416344 hasConcept C81363708 @default.
• W3198416344 hasConcept C85817219 @default.
• W3198416344 hasConceptScore W3198416344C11413529 @default.
• W3198416344 hasConceptScore W3198416344C121332964 @default.
• W3198416344 hasConceptScore W3198416344C130367717 @default.
• W3198416344 hasConceptScore W3198416344C138885662 @default.
• W3198416344 hasConceptScore W3198416344C153180895 @default.
• W3198416344 hasConceptScore W3198416344C154945302 @default.
• W3198416344 hasConceptScore W3198416344C158693339 @default.

• next