Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100624467> ?p ?o ?g. }
- W3100624467 endingPage "46" @default.
- W3100624467 startingPage "31" @default.
- W3100624467 abstract "Model-based method and data-based method are two basic approaches for the design of wireless communication systems. Model-based methods suffer from inaccurate modeling assumptions due to excessively complex environment. Recently, data-based methods have achieved remarkable performances in the communication system design without the knowledge of accurate model but encounter some challenges such as, lack of available labelled training data and explainability. In this paper, we propose a novel hybrid idea to integrate the strengths of both data and model-based methods, named model refinement learning, which is training affordable, theoretically interpretable and self-adapting. To show the idea more concretely, a novel channel estimation algorithm is proposed in the multiple-input single-output (MISO) system in the case where the noise model is unknown. In particular, we utilize a universal mixture of Gaussian (MoG) model, which can adaptively adjust the involved parameters to fit the true noise distribution by using observed data. We propose a novel variational inference framework to achieve automatical noise model refinement and design the corresponding online channel estimator. To reduce the online algorithm overhead, we propose a decoupled variational Bayesian method to achieve linear computational complexity. Simulations show that our proposed method outperforms both the model-based and data-based counterparts." @default.
- W3100624467 created "2020-11-23" @default.
- W3100624467 creator A5015681757 @default.
- W3100624467 creator A5062588973 @default.
- W3100624467 creator A5078181662 @default.
- W3100624467 date "2021-01-01" @default.
- W3100624467 modified "2023-10-15" @default.
- W3100624467 title "Model Refinement Learning and an Example on Channel Estimation With Universal Noise Model" @default.
- W3100624467 cites W1763302039 @default.
- W3100624467 cites W2026933032 @default.
- W3100624467 cites W2032669396 @default.
- W3100624467 cites W2114355534 @default.
- W3100624467 cites W2147035723 @default.
- W3100624467 cites W2151967501 @default.
- W3100624467 cites W2160255741 @default.
- W3100624467 cites W2167823677 @default.
- W3100624467 cites W2171998198 @default.
- W3100624467 cites W2182565882 @default.
- W3100624467 cites W2254069717 @default.
- W3100624467 cites W2341236332 @default.
- W3100624467 cites W2589785008 @default.
- W3100624467 cites W2606697812 @default.
- W3100624467 cites W2612472936 @default.
- W3100624467 cites W2620303912 @default.
- W3100624467 cites W2743678626 @default.
- W3100624467 cites W2745541172 @default.
- W3100624467 cites W2786361328 @default.
- W3100624467 cites W2805005199 @default.
- W3100624467 cites W2817829786 @default.
- W3100624467 cites W2884140695 @default.
- W3100624467 cites W2889153869 @default.
- W3100624467 cites W2893910439 @default.
- W3100624467 cites W2897042325 @default.
- W3100624467 cites W2946356742 @default.
- W3100624467 cites W2960563976 @default.
- W3100624467 cites W2962956060 @default.
- W3100624467 cites W2962964572 @default.
- W3100624467 cites W2963000651 @default.
- W3100624467 cites W2963190722 @default.
- W3100624467 cites W2963290405 @default.
- W3100624467 cites W2963408536 @default.
- W3100624467 cites W2963836746 @default.
- W3100624467 cites W2964021722 @default.
- W3100624467 cites W2974170798 @default.
- W3100624467 cites W2990764713 @default.
- W3100624467 cites W3004579445 @default.
- W3100624467 cites W3011225834 @default.
- W3100624467 cites W4293052541 @default.
- W3100624467 doi "https://doi.org/10.1109/jsac.2020.3036964" @default.
- W3100624467 hasPublicationYear "2021" @default.
- W3100624467 type Work @default.
- W3100624467 sameAs 3100624467 @default.
- W3100624467 citedByCount "10" @default.
- W3100624467 countsByYear W31006244672021 @default.
- W3100624467 countsByYear W31006244672022 @default.
- W3100624467 countsByYear W31006244672023 @default.
- W3100624467 crossrefType "journal-article" @default.
- W3100624467 hasAuthorship W3100624467A5015681757 @default.
- W3100624467 hasAuthorship W3100624467A5062588973 @default.
- W3100624467 hasAuthorship W3100624467A5078181662 @default.
- W3100624467 hasConcept C105795698 @default.
- W3100624467 hasConcept C107673813 @default.
- W3100624467 hasConcept C111919701 @default.
- W3100624467 hasConcept C11413529 @default.
- W3100624467 hasConcept C115961682 @default.
- W3100624467 hasConcept C119857082 @default.
- W3100624467 hasConcept C127162648 @default.
- W3100624467 hasConcept C154945302 @default.
- W3100624467 hasConcept C160234255 @default.
- W3100624467 hasConcept C185429906 @default.
- W3100624467 hasConcept C2776214188 @default.
- W3100624467 hasConcept C2779960059 @default.
- W3100624467 hasConcept C31258907 @default.
- W3100624467 hasConcept C33923547 @default.
- W3100624467 hasConcept C41008148 @default.
- W3100624467 hasConcept C67186912 @default.
- W3100624467 hasConcept C77088390 @default.
- W3100624467 hasConcept C99498987 @default.
- W3100624467 hasConceptScore W3100624467C105795698 @default.
- W3100624467 hasConceptScore W3100624467C107673813 @default.
- W3100624467 hasConceptScore W3100624467C111919701 @default.
- W3100624467 hasConceptScore W3100624467C11413529 @default.
- W3100624467 hasConceptScore W3100624467C115961682 @default.
- W3100624467 hasConceptScore W3100624467C119857082 @default.
- W3100624467 hasConceptScore W3100624467C127162648 @default.
- W3100624467 hasConceptScore W3100624467C154945302 @default.
- W3100624467 hasConceptScore W3100624467C160234255 @default.
- W3100624467 hasConceptScore W3100624467C185429906 @default.
- W3100624467 hasConceptScore W3100624467C2776214188 @default.
- W3100624467 hasConceptScore W3100624467C2779960059 @default.
- W3100624467 hasConceptScore W3100624467C31258907 @default.
- W3100624467 hasConceptScore W3100624467C33923547 @default.
- W3100624467 hasConceptScore W3100624467C41008148 @default.
- W3100624467 hasConceptScore W3100624467C67186912 @default.
- W3100624467 hasConceptScore W3100624467C77088390 @default.
- W3100624467 hasConceptScore W3100624467C99498987 @default.
- W3100624467 hasFunder F4320321001 @default.
- W3100624467 hasIssue "1" @default.