FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129293716> ?p ?o ?g. }

• W3129293716 endingPage "19" @default.
• W3129293716 startingPage "1" @default.
• W3129293716 abstract "Band selection is an important step in efficient processing of hyperspectral images (HSIs), which can be seen as the combination of powerful band search technique and effective evaluation criterion. The existing deep-learning-based methods make the network parameters sparse to search the spectral bands using threshold-based functions or regularization terms. These methods may lead to an intractable optimization problem. Furthermore, these methods need to repeatedly train deep networks for evaluating candidate band subsets. In this article, we formalize hyperspectral band selection as a reinforcement learning (RL) problem. Band search is regarded as a sequential decision-making process, where each state in the search space is a feasible band subset. To evaluate each state, a semisupervised convolutional neural network (CNN), called EvaluateNet, is constructed by adding the intraclass compactness constraint of both limited labeled and sufficient unlabeled samples. A simple stochastic band sampling method is designed to train EvaluateNet, making it possible to efficiently evaluate without any fine-tuning. In RL, new reward functions are defined by taking the EvaluateNet and the penalty of repeated selection into account. Finally, advantage actor–critic algorithms are designed to explore in the state space and select the band subset according to the expected accumulated reward. The experimental results on HSI data sets demonstrate the effectiveness and efficiency of the proposed algorithms for hyperspectral band selection." @default.
• W3129293716 created "2021-03-01" @default.
• W3129293716 creator A5031776699 @default.
• W3129293716 creator A5032503755 @default.
• W3129293716 creator A5040301865 @default.
• W3129293716 creator A5045546082 @default.
• W3129293716 creator A5049776440 @default.
• W3129293716 creator A5050630882 @default.
• W3129293716 creator A5054791684 @default.
• W3129293716 date "2022-01-01" @default.
• W3129293716 modified "2023-10-16" @default.
• W3129293716 title "Deep Reinforcement Learning for Semisupervised Hyperspectral Band Selection" @default.
• W3129293716 cites W1523989055 @default.
• W3129293716 cites W1932531222 @default.
• W3129293716 cites W1993022127 @default.
• W3129293716 cites W1995333990 @default.
• W3129293716 cites W1995450389 @default.
• W3129293716 cites W2005871861 @default.
• W3129293716 cites W2042294722 @default.
• W3129293716 cites W2043945532 @default.
• W3129293716 cites W2044439250 @default.
• W3129293716 cites W2044860242 @default.
• W3129293716 cites W2064675550 @default.
• W3129293716 cites W2067983477 @default.
• W3129293716 cites W2069469310 @default.
• W3129293716 cites W2119717200 @default.
• W3129293716 cites W2124834959 @default.
• W3129293716 cites W2138038253 @default.
• W3129293716 cites W2143277109 @default.
• W3129293716 cites W2150990614 @default.
• W3129293716 cites W2154053567 @default.
• W3129293716 cites W2165835468 @default.
• W3129293716 cites W2506684654 @default.
• W3129293716 cites W2516282711 @default.
• W3129293716 cites W2548090596 @default.
• W3129293716 cites W2604319603 @default.
• W3129293716 cites W2613070336 @default.
• W3129293716 cites W2764276316 @default.
• W3129293716 cites W2769143033 @default.
• W3129293716 cites W2774446296 @default.
• W3129293716 cites W2791684669 @default.
• W3129293716 cites W2896340099 @default.
• W3129293716 cites W2919520811 @default.
• W3129293716 cites W2937638900 @default.
• W3129293716 cites W2984618279 @default.
• W3129293716 cites W2985526435 @default.
• W3129293716 cites W2988365422 @default.
• W3129293716 cites W2991616716 @default.
• W3129293716 cites W3005414792 @default.
• W3129293716 cites W3010420609 @default.
• W3129293716 cites W3011308832 @default.
• W3129293716 cites W3023065102 @default.
• W3129293716 cites W3047317383 @default.
• W3129293716 cites W3102274762 @default.
• W3129293716 cites W3123212791 @default.
• W3129293716 cites W4236558809 @default.
• W3129293716 doi "https://doi.org/10.1109/tgrs.2021.3049372" @default.
• W3129293716 hasPublicationYear "2022" @default.
• W3129293716 type Work @default.
• W3129293716 sameAs 3129293716 @default.
• W3129293716 citedByCount "22" @default.
• W3129293716 countsByYear W31292937162021 @default.
• W3129293716 countsByYear W31292937162022 @default.
• W3129293716 countsByYear W31292937162023 @default.
• W3129293716 crossrefType "journal-article" @default.
• W3129293716 hasAuthorship W3129293716A5031776699 @default.
• W3129293716 hasAuthorship W3129293716A5032503755 @default.
• W3129293716 hasAuthorship W3129293716A5040301865 @default.
• W3129293716 hasAuthorship W3129293716A5045546082 @default.
• W3129293716 hasAuthorship W3129293716A5049776440 @default.
• W3129293716 hasAuthorship W3129293716A5050630882 @default.
• W3129293716 hasAuthorship W3129293716A5054791684 @default.
• W3129293716 hasConcept C108583219 @default.
• W3129293716 hasConcept C119857082 @default.
• W3129293716 hasConcept C153180895 @default.
• W3129293716 hasConcept C154945302 @default.
• W3129293716 hasConcept C159078339 @default.
• W3129293716 hasConcept C2776135515 @default.
• W3129293716 hasConcept C41008148 @default.
• W3129293716 hasConcept C81363708 @default.
• W3129293716 hasConcept C81917197 @default.
• W3129293716 hasConcept C97541855 @default.
• W3129293716 hasConceptScore W3129293716C108583219 @default.
• W3129293716 hasConceptScore W3129293716C119857082 @default.
• W3129293716 hasConceptScore W3129293716C153180895 @default.
• W3129293716 hasConceptScore W3129293716C154945302 @default.
• W3129293716 hasConceptScore W3129293716C159078339 @default.
• W3129293716 hasConceptScore W3129293716C2776135515 @default.
• W3129293716 hasConceptScore W3129293716C41008148 @default.
• W3129293716 hasConceptScore W3129293716C81363708 @default.
• W3129293716 hasConceptScore W3129293716C81917197 @default.
• W3129293716 hasConceptScore W3129293716C97541855 @default.
• W3129293716 hasFunder F4320321001 @default.
• W3129293716 hasFunder F4320330207 @default.
• W3129293716 hasLocation W31292937161 @default.
• W3129293716 hasOpenAccess W3129293716 @default.
• W3129293716 hasPrimaryLocation W31292937161 @default.
• W3129293716 hasRelatedWork W2425127026 @default.

• next