Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307292499> ?p ?o ?g. }
- W4307292499 endingPage "103789" @default.
- W4307292499 startingPage "103789" @default.
- W4307292499 abstract "Over the last few decades, lots of model-driven methods have been developed for model-based compressed sensing (CS), in which the inherent structures of sparse signals are exploited as priors to promote reconstruction accuracy and robustness. Although these methods obtained positive results, there still exist low prior utilizations. The single model-driven fashion is hard to completely express structured priors. Motivated by the recent flourishing studies of deep learning, we combine the model-based framework of the pattern-coupled sparse Bayesian learning (PC-SBL) with data-driven deep learning method to form a double-driven architecture, dubbed as PC-DINN. First, a generalized model of pattern-coupled Bayesian priors is developed to characterize structured properties, in which learnable scale parameters are generated by a heterogeneous process. Second, we unroll the iterative sparse Bayesian learning (SBL) algorithm to form an interpretable deep iterative neural network, and then treat all the learnable scale parameters of the prior model as weights to be learned. To the best of our knowledge, this is the first combination of model-based SBL and data-driven methods for structured CS. Simulation results suggest that for both the structured sparse signals of block sparsity and tree sparsity, the proposed PC-DINN not only achieves favorable reconstruction accuracy but also overcomes the vulnerability of parameter choice in the framework of PC-SBL." @default.
- W4307292499 created "2022-10-31" @default.
- W4307292499 creator A5006484983 @default.
- W4307292499 creator A5031004784 @default.
- W4307292499 creator A5043214550 @default.
- W4307292499 creator A5052241503 @default.
- W4307292499 creator A5084224429 @default.
- W4307292499 creator A5090371252 @default.
- W4307292499 date "2023-01-01" @default.
- W4307292499 modified "2023-10-16" @default.
- W4307292499 title "A deep iterative neural network for structured compressed sensing based on generalized pattern-coupled sparse Bayesian learning" @default.
- W4307292499 cites W1857867064 @default.
- W4307292499 cites W1974550829 @default.
- W4307292499 cites W1985894000 @default.
- W4307292499 cites W2025950086 @default.
- W4307292499 cites W2033419225 @default.
- W4307292499 cites W2049502219 @default.
- W4307292499 cites W2071282831 @default.
- W4307292499 cites W2071284784 @default.
- W4307292499 cites W2119667497 @default.
- W4307292499 cites W2127271355 @default.
- W4307292499 cites W213726709 @default.
- W4307292499 cites W2145096794 @default.
- W4307292499 cites W2151932824 @default.
- W4307292499 cites W2292697821 @default.
- W4307292499 cites W2522427398 @default.
- W4307292499 cites W2596873572 @default.
- W4307292499 cites W2729804518 @default.
- W4307292499 cites W2790212948 @default.
- W4307292499 cites W2807986908 @default.
- W4307292499 cites W2884140695 @default.
- W4307292499 cites W2889049182 @default.
- W4307292499 cites W2902719825 @default.
- W4307292499 cites W2904155163 @default.
- W4307292499 cites W2956474262 @default.
- W4307292499 cites W2963322354 @default.
- W4307292499 cites W2964058567 @default.
- W4307292499 cites W2968867437 @default.
- W4307292499 cites W2979418163 @default.
- W4307292499 cites W2995445161 @default.
- W4307292499 cites W3027849421 @default.
- W4307292499 cites W3100456593 @default.
- W4307292499 cites W3125735862 @default.
- W4307292499 cites W3181549535 @default.
- W4307292499 cites W4213296448 @default.
- W4307292499 doi "https://doi.org/10.1016/j.dsp.2022.103789" @default.
- W4307292499 hasPublicationYear "2023" @default.
- W4307292499 type Work @default.
- W4307292499 citedByCount "0" @default.
- W4307292499 crossrefType "journal-article" @default.
- W4307292499 hasAuthorship W4307292499A5006484983 @default.
- W4307292499 hasAuthorship W4307292499A5031004784 @default.
- W4307292499 hasAuthorship W4307292499A5043214550 @default.
- W4307292499 hasAuthorship W4307292499A5052241503 @default.
- W4307292499 hasAuthorship W4307292499A5084224429 @default.
- W4307292499 hasAuthorship W4307292499A5090371252 @default.
- W4307292499 hasConcept C104317684 @default.
- W4307292499 hasConcept C107673813 @default.
- W4307292499 hasConcept C108583219 @default.
- W4307292499 hasConcept C11413529 @default.
- W4307292499 hasConcept C119857082 @default.
- W4307292499 hasConcept C124851039 @default.
- W4307292499 hasConcept C13280743 @default.
- W4307292499 hasConcept C153180895 @default.
- W4307292499 hasConcept C154945302 @default.
- W4307292499 hasConcept C160234255 @default.
- W4307292499 hasConcept C177769412 @default.
- W4307292499 hasConcept C185592680 @default.
- W4307292499 hasConcept C185798385 @default.
- W4307292499 hasConcept C205649164 @default.
- W4307292499 hasConcept C41008148 @default.
- W4307292499 hasConcept C50644808 @default.
- W4307292499 hasConcept C55493867 @default.
- W4307292499 hasConcept C63479239 @default.
- W4307292499 hasConceptScore W4307292499C104317684 @default.
- W4307292499 hasConceptScore W4307292499C107673813 @default.
- W4307292499 hasConceptScore W4307292499C108583219 @default.
- W4307292499 hasConceptScore W4307292499C11413529 @default.
- W4307292499 hasConceptScore W4307292499C119857082 @default.
- W4307292499 hasConceptScore W4307292499C124851039 @default.
- W4307292499 hasConceptScore W4307292499C13280743 @default.
- W4307292499 hasConceptScore W4307292499C153180895 @default.
- W4307292499 hasConceptScore W4307292499C154945302 @default.
- W4307292499 hasConceptScore W4307292499C160234255 @default.
- W4307292499 hasConceptScore W4307292499C177769412 @default.
- W4307292499 hasConceptScore W4307292499C185592680 @default.
- W4307292499 hasConceptScore W4307292499C185798385 @default.
- W4307292499 hasConceptScore W4307292499C205649164 @default.
- W4307292499 hasConceptScore W4307292499C41008148 @default.
- W4307292499 hasConceptScore W4307292499C50644808 @default.
- W4307292499 hasConceptScore W4307292499C55493867 @default.
- W4307292499 hasConceptScore W4307292499C63479239 @default.
- W4307292499 hasFunder F4320321001 @default.
- W4307292499 hasFunder F4320322665 @default.
- W4307292499 hasFunder F4320325626 @default.
- W4307292499 hasLocation W43072924991 @default.
- W4307292499 hasOpenAccess W4307292499 @default.
- W4307292499 hasPrimaryLocation W43072924991 @default.