Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172159586> ?p ?o ?g. }
- W3172159586 endingPage "1710" @default.
- W3172159586 startingPage "1697" @default.
- W3172159586 abstract "In this paper, we propose a novel deep unsupervised learning-based approach that jointly optimizes antenna selection and hybrid beamforming to improve the hardware and spectral efficiencies of massive multiple-input-multiple-output (MIMO) downlink systems. By employing ResNet to extract features from the channel matrices, two neural networks, i.e., the antenna selection network (ASNet) and the hybrid beamforming network (BFNet), are respectively proposed for dynamic antenna selection and hybrid beamformer design. Furthermore, a deep probabilistic subsampling trick and a specially designed quantization function are respectively developed for ASNet and BFNet to preserve the differentiability while embedding discrete constraints into the network structures. With the aid of a flexibly designed loss function, ASNet and BFNet are jointly trained in a phased unsupervised way, which avoids the prohibitive computational cost of acquiring training labels in supervised learning. Simulation results demonstrate the advantage of the proposed approach over conventional optimization-based algorithms in terms of both the achieved rate and the computational complexity." @default.
- W3172159586 created "2021-06-22" @default.
- W3172159586 creator A5050402661 @default.
- W3172159586 creator A5054284011 @default.
- W3172159586 creator A5064073489 @default.
- W3172159586 creator A5075551339 @default.
- W3172159586 creator A5086769157 @default.
- W3172159586 date "2022-03-01" @default.
- W3172159586 modified "2023-10-03" @default.
- W3172159586 title "Deep Unsupervised Learning for Joint Antenna Selection and Hybrid Beamforming" @default.
- W3172159586 cites W1586395257 @default.
- W3172159586 cites W1932847118 @default.
- W3172159586 cites W2004294022 @default.
- W3172159586 cites W2053521124 @default.
- W3172159586 cites W2075148031 @default.
- W3172159586 cites W2099030964 @default.
- W3172159586 cites W2129213108 @default.
- W3172159586 cites W2130134073 @default.
- W3172159586 cites W2149527114 @default.
- W3172159586 cites W2194775991 @default.
- W3172159586 cites W2195833401 @default.
- W3172159586 cites W2259391824 @default.
- W3172159586 cites W2272804037 @default.
- W3172159586 cites W2477563955 @default.
- W3172159586 cites W2519232304 @default.
- W3172159586 cites W2525086471 @default.
- W3172159586 cites W2587991392 @default.
- W3172159586 cites W2729652156 @default.
- W3172159586 cites W2767179702 @default.
- W3172159586 cites W2777236243 @default.
- W3172159586 cites W2885409810 @default.
- W3172159586 cites W2899528673 @default.
- W3172159586 cites W2905885786 @default.
- W3172159586 cites W2921187277 @default.
- W3172159586 cites W2943928690 @default.
- W3172159586 cites W2962819920 @default.
- W3172159586 cites W2963190722 @default.
- W3172159586 cites W2963290405 @default.
- W3172159586 cites W2963504849 @default.
- W3172159586 cites W2964021722 @default.
- W3172159586 cites W2964468371 @default.
- W3172159586 cites W2992096220 @default.
- W3172159586 cites W3035449691 @default.
- W3172159586 cites W3039366958 @default.
- W3172159586 cites W3102812201 @default.
- W3172159586 cites W3104742473 @default.
- W3172159586 cites W3104804153 @default.
- W3172159586 cites W3106282754 @default.
- W3172159586 cites W3117321202 @default.
- W3172159586 cites W3117922432 @default.
- W3172159586 cites W3122971299 @default.
- W3172159586 cites W3126373016 @default.
- W3172159586 cites W3134410998 @default.
- W3172159586 cites W3158088703 @default.
- W3172159586 cites W3165862203 @default.
- W3172159586 cites W3166129236 @default.
- W3172159586 cites W4250515024 @default.
- W3172159586 doi "https://doi.org/10.1109/tcomm.2022.3143122" @default.
- W3172159586 hasPublicationYear "2022" @default.
- W3172159586 type Work @default.
- W3172159586 sameAs 3172159586 @default.
- W3172159586 citedByCount "14" @default.
- W3172159586 countsByYear W31721595862022 @default.
- W3172159586 countsByYear W31721595862023 @default.
- W3172159586 crossrefType "journal-article" @default.
- W3172159586 hasAuthorship W3172159586A5050402661 @default.
- W3172159586 hasAuthorship W3172159586A5054284011 @default.
- W3172159586 hasAuthorship W3172159586A5064073489 @default.
- W3172159586 hasAuthorship W3172159586A5075551339 @default.
- W3172159586 hasAuthorship W3172159586A5086769157 @default.
- W3172159586 hasBestOaLocation W31721595862 @default.
- W3172159586 hasConcept C108583219 @default.
- W3172159586 hasConcept C11413529 @default.
- W3172159586 hasConcept C119857082 @default.
- W3172159586 hasConcept C138660444 @default.
- W3172159586 hasConcept C154945302 @default.
- W3172159586 hasConcept C179799912 @default.
- W3172159586 hasConcept C207987634 @default.
- W3172159586 hasConcept C21822782 @default.
- W3172159586 hasConcept C41008148 @default.
- W3172159586 hasConcept C50644808 @default.
- W3172159586 hasConcept C54197355 @default.
- W3172159586 hasConcept C76155785 @default.
- W3172159586 hasConcept C8038995 @default.
- W3172159586 hasConcept C81917197 @default.
- W3172159586 hasConceptScore W3172159586C108583219 @default.
- W3172159586 hasConceptScore W3172159586C11413529 @default.
- W3172159586 hasConceptScore W3172159586C119857082 @default.
- W3172159586 hasConceptScore W3172159586C138660444 @default.
- W3172159586 hasConceptScore W3172159586C154945302 @default.
- W3172159586 hasConceptScore W3172159586C179799912 @default.
- W3172159586 hasConceptScore W3172159586C207987634 @default.
- W3172159586 hasConceptScore W3172159586C21822782 @default.
- W3172159586 hasConceptScore W3172159586C41008148 @default.
- W3172159586 hasConceptScore W3172159586C50644808 @default.
- W3172159586 hasConceptScore W3172159586C54197355 @default.
- W3172159586 hasConceptScore W3172159586C76155785 @default.
- W3172159586 hasConceptScore W3172159586C8038995 @default.