Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202667300> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3202667300 endingPage "3877" @default.
- W3202667300 startingPage "3873" @default.
- W3202667300 abstract "Channel state information (CSI) is a critical part for massive multiple-input multiple-output (MIMO) system. However, it is a big challenge to send a large amount of CSI from the receiver to the transmitter with limited channel resources. In this letter, we propose asymmetric convolution-based autoencoder framework (ACCsiNet) to handle the CSI compression and decompression problem. Specifically, asymmetric convolution block (AC-Block) is used to enhance the feature extraction ability of convolution. Further, a lightweight method is applied, which can greatly reduce the storage space at the receiver. Considering the practical deployment, multi-model fusion schemes including multi-rate and multi-scenario fusion are also discussed to strengthen the generalization ability of the network. Experimental results show that the proposed ACCsiNet can improve the NMSE and cosine similarity <inline-formula> <tex-math notation=LaTeX>$rho $ </tex-math></inline-formula> performance, especially for outdoor scenario. The results also verify that both the lightweight and multi-model fusion schemes can reach a near-optimal performance of the proposed ACCsiNet, but further significantly reduce the parameter amount by more than 83% and 90%, respectively." @default.
- W3202667300 created "2021-10-11" @default.
- W3202667300 creator A5052913836 @default.
- W3202667300 creator A5071081238 @default.
- W3202667300 creator A5081072662 @default.
- W3202667300 creator A5082151094 @default.
- W3202667300 date "2021-12-01" @default.
- W3202667300 modified "2023-10-17" @default.
- W3202667300 title "ACCsiNet: Asymmetric Convolution-Based Autoencoder Framework for Massive MIMO CSI Feedback" @default.
- W3202667300 cites W2023535408 @default.
- W3202667300 cites W2072079297 @default.
- W3202667300 cites W2901240584 @default.
- W3202667300 cites W2963145597 @default.
- W3202667300 cites W2981609437 @default.
- W3202667300 cites W3003689553 @default.
- W3202667300 cites W3045610411 @default.
- W3202667300 doi "https://doi.org/10.1109/lcomm.2021.3116864" @default.
- W3202667300 hasPublicationYear "2021" @default.
- W3202667300 type Work @default.
- W3202667300 sameAs 3202667300 @default.
- W3202667300 citedByCount "4" @default.
- W3202667300 countsByYear W32026673002022 @default.
- W3202667300 countsByYear W32026673002023 @default.
- W3202667300 crossrefType "journal-article" @default.
- W3202667300 hasAuthorship W3202667300A5052913836 @default.
- W3202667300 hasAuthorship W3202667300A5071081238 @default.
- W3202667300 hasAuthorship W3202667300A5081072662 @default.
- W3202667300 hasAuthorship W3202667300A5082151094 @default.
- W3202667300 hasConcept C101738243 @default.
- W3202667300 hasConcept C108583219 @default.
- W3202667300 hasConcept C113775141 @default.
- W3202667300 hasConcept C11413529 @default.
- W3202667300 hasConcept C127162648 @default.
- W3202667300 hasConcept C134306372 @default.
- W3202667300 hasConcept C148063708 @default.
- W3202667300 hasConcept C154945302 @default.
- W3202667300 hasConcept C177148314 @default.
- W3202667300 hasConcept C207987634 @default.
- W3202667300 hasConcept C2524010 @default.
- W3202667300 hasConcept C2777210771 @default.
- W3202667300 hasConcept C33923547 @default.
- W3202667300 hasConcept C41008148 @default.
- W3202667300 hasConcept C45347329 @default.
- W3202667300 hasConcept C47798520 @default.
- W3202667300 hasConcept C50644808 @default.
- W3202667300 hasConcept C555944384 @default.
- W3202667300 hasConcept C76155785 @default.
- W3202667300 hasConcept C80444323 @default.
- W3202667300 hasConceptScore W3202667300C101738243 @default.
- W3202667300 hasConceptScore W3202667300C108583219 @default.
- W3202667300 hasConceptScore W3202667300C113775141 @default.
- W3202667300 hasConceptScore W3202667300C11413529 @default.
- W3202667300 hasConceptScore W3202667300C127162648 @default.
- W3202667300 hasConceptScore W3202667300C134306372 @default.
- W3202667300 hasConceptScore W3202667300C148063708 @default.
- W3202667300 hasConceptScore W3202667300C154945302 @default.
- W3202667300 hasConceptScore W3202667300C177148314 @default.
- W3202667300 hasConceptScore W3202667300C207987634 @default.
- W3202667300 hasConceptScore W3202667300C2524010 @default.
- W3202667300 hasConceptScore W3202667300C2777210771 @default.
- W3202667300 hasConceptScore W3202667300C33923547 @default.
- W3202667300 hasConceptScore W3202667300C41008148 @default.
- W3202667300 hasConceptScore W3202667300C45347329 @default.
- W3202667300 hasConceptScore W3202667300C47798520 @default.
- W3202667300 hasConceptScore W3202667300C50644808 @default.
- W3202667300 hasConceptScore W3202667300C555944384 @default.
- W3202667300 hasConceptScore W3202667300C76155785 @default.
- W3202667300 hasConceptScore W3202667300C80444323 @default.
- W3202667300 hasFunder F4320321001 @default.
- W3202667300 hasFunder F4320322919 @default.
- W3202667300 hasIssue "12" @default.
- W3202667300 hasLocation W32026673001 @default.
- W3202667300 hasOpenAccess W3202667300 @default.
- W3202667300 hasPrimaryLocation W32026673001 @default.
- W3202667300 hasRelatedWork W2004252678 @default.
- W3202667300 hasRelatedWork W2014560584 @default.
- W3202667300 hasRelatedWork W2022380002 @default.
- W3202667300 hasRelatedWork W2025723618 @default.
- W3202667300 hasRelatedWork W2059045613 @default.
- W3202667300 hasRelatedWork W2085657193 @default.
- W3202667300 hasRelatedWork W2137509205 @default.
- W3202667300 hasRelatedWork W2785353499 @default.
- W3202667300 hasRelatedWork W3081077581 @default.
- W3202667300 hasRelatedWork W2129498500 @default.
- W3202667300 hasVolume "25" @default.
- W3202667300 isParatext "false" @default.
- W3202667300 isRetracted "false" @default.
- W3202667300 magId "3202667300" @default.
- W3202667300 workType "article" @default.