Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159843227> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3159843227 endingPage "1184" @default.
- W3159843227 startingPage "1170" @default.
- W3159843227 abstract "The spectrum cartography (SC) technique constructs multi-domain (e.g., frequency, space, and time) radio frequency (RF) maps from limited measurements, which can be viewed as an ill-posed tensor completion problem. Model-based cartography techniques often rely on handcrafted priors (e.g., sparsity, smoothness and low-rank structures) for the completion task. Such priors may be inadequate to capture the essence of complex wireless environments -- especially when severe shadowing happens. To circumvent such challenges, offline-trained deep neural models of radio maps were considered for SC, as deep neural networks (DNNs) are able to learn intricate underlying structures from data. However, such deep learning (DL)-based SC approaches encounter serious challenges in both off-line model learning (training) and completion (generalization), possibly because the latent state space for generating the radio maps is prohibitively large. In this work, an emitter radio map disaggregation-based approach is proposed, under which only individual emitters' radio maps are modeled by DNNs. This way, the learning and generalization challenges can both be substantially alleviated. Using the learned DNNs, a fast nonnegative matrix factorization-based two-stage SC method and a performance-enhanced iterative optimization algorithm are proposed. Theoretical aspects -- such as recoverability of the radio tensor, sample complexity, and noise robustness -- under the proposed framework are characterized, and such theoretical properties have been elusive in the context of DL-based radio tensor completion. Experiments using synthetic and real-data from indoor and heavily shadowed environments are employed to showcase the effectiveness of the proposed methods." @default.
- W3159843227 created "2021-05-10" @default.
- W3159843227 creator A5015075381 @default.
- W3159843227 creator A5016900183 @default.
- W3159843227 creator A5085949016 @default.
- W3159843227 date "2022-01-01" @default.
- W3159843227 modified "2023-10-01" @default.
- W3159843227 title "Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models" @default.
- W3159843227 cites W1814500939 @default.
- W3159843227 cites W1885765327 @default.
- W3159843227 cites W1964735835 @default.
- W3159843227 cites W1968436459 @default.
- W3159843227 cites W1983559465 @default.
- W3159843227 cites W2000045479 @default.
- W3159843227 cites W2003688737 @default.
- W3159843227 cites W2039806043 @default.
- W3159843227 cites W2040399008 @default.
- W3159843227 cites W2070424424 @default.
- W3159843227 cites W2075665712 @default.
- W3159843227 cites W2081540728 @default.
- W3159843227 cites W2091484400 @default.
- W3159843227 cites W2101840010 @default.
- W3159843227 cites W2108924122 @default.
- W3159843227 cites W2125118959 @default.
- W3159843227 cites W2125126993 @default.
- W3159843227 cites W2157879939 @default.
- W3159843227 cites W2181680249 @default.
- W3159843227 cites W2343706002 @default.
- W3159843227 cites W2414995726 @default.
- W3159843227 cites W2712405193 @default.
- W3159843227 cites W2752365628 @default.
- W3159843227 cites W2791973964 @default.
- W3159843227 cites W2883649322 @default.
- W3159843227 cites W2907930484 @default.
- W3159843227 cites W2989504803 @default.
- W3159843227 cites W2991033093 @default.
- W3159843227 cites W2998379392 @default.
- W3159843227 cites W3012526467 @default.
- W3159843227 cites W3046067353 @default.
- W3159843227 cites W3085097441 @default.
- W3159843227 cites W3100202987 @default.
- W3159843227 cites W3114089334 @default.
- W3159843227 cites W595252221 @default.
- W3159843227 doi "https://doi.org/10.1109/tsp.2022.3145190" @default.
- W3159843227 hasPublicationYear "2022" @default.
- W3159843227 type Work @default.
- W3159843227 sameAs 3159843227 @default.
- W3159843227 citedByCount "9" @default.
- W3159843227 countsByYear W31598432272022 @default.
- W3159843227 countsByYear W31598432272023 @default.
- W3159843227 crossrefType "journal-article" @default.
- W3159843227 hasAuthorship W3159843227A5015075381 @default.
- W3159843227 hasAuthorship W3159843227A5016900183 @default.
- W3159843227 hasAuthorship W3159843227A5085949016 @default.
- W3159843227 hasBestOaLocation W31598432272 @default.
- W3159843227 hasConcept C104317684 @default.
- W3159843227 hasConcept C107673813 @default.
- W3159843227 hasConcept C108583219 @default.
- W3159843227 hasConcept C11413529 @default.
- W3159843227 hasConcept C119857082 @default.
- W3159843227 hasConcept C154945302 @default.
- W3159843227 hasConcept C177769412 @default.
- W3159843227 hasConcept C185592680 @default.
- W3159843227 hasConcept C41008148 @default.
- W3159843227 hasConcept C55493867 @default.
- W3159843227 hasConcept C63479239 @default.
- W3159843227 hasConceptScore W3159843227C104317684 @default.
- W3159843227 hasConceptScore W3159843227C107673813 @default.
- W3159843227 hasConceptScore W3159843227C108583219 @default.
- W3159843227 hasConceptScore W3159843227C11413529 @default.
- W3159843227 hasConceptScore W3159843227C119857082 @default.
- W3159843227 hasConceptScore W3159843227C154945302 @default.
- W3159843227 hasConceptScore W3159843227C177769412 @default.
- W3159843227 hasConceptScore W3159843227C185592680 @default.
- W3159843227 hasConceptScore W3159843227C41008148 @default.
- W3159843227 hasConceptScore W3159843227C55493867 @default.
- W3159843227 hasConceptScore W3159843227C63479239 @default.
- W3159843227 hasLocation W31598432271 @default.
- W3159843227 hasLocation W31598432272 @default.
- W3159843227 hasLocation W31598432273 @default.
- W3159843227 hasOpenAccess W3159843227 @default.
- W3159843227 hasPrimaryLocation W31598432271 @default.
- W3159843227 hasRelatedWork W2795261237 @default.
- W3159843227 hasRelatedWork W3014300295 @default.
- W3159843227 hasRelatedWork W3164822677 @default.
- W3159843227 hasRelatedWork W4223943233 @default.
- W3159843227 hasRelatedWork W4225161397 @default.
- W3159843227 hasRelatedWork W4312200629 @default.
- W3159843227 hasRelatedWork W4360585206 @default.
- W3159843227 hasRelatedWork W4364306694 @default.
- W3159843227 hasRelatedWork W4380075502 @default.
- W3159843227 hasRelatedWork W4380086463 @default.
- W3159843227 hasVolume "70" @default.
- W3159843227 isParatext "false" @default.
- W3159843227 isRetracted "false" @default.
- W3159843227 magId "3159843227" @default.
- W3159843227 workType "article" @default.