Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113122707> ?p ?o ?g. }
- W3113122707 endingPage "2332" @default.
- W3113122707 startingPage "2318" @default.
- W3113122707 abstract "Machine learning (ML) starts to be widely used to enhance the performance of multi-user multiple-input multiple-output (MU-MIMO) receivers. However, it is still unclear if such methods are truly competitive with respect to conventional methods in realistic scenarios and under practical constraints. In addition to enabling accurate signal reconstruction on realistic channel models, MU-MIMO receive algorithms must allow for easy adaptation to a varying number of users without the need for retraining. In contrast to existing work, we propose an machine learning (ML)-enhanced MU-MIMO receiver that builds on top of a conventional linear minimum mean squared error (LMMSE) architecture. It preserves the interpretability and scalability of the LMMSE receiver, while improving its accuracy in two ways. First, convolutional neural networks (CNNs) are used to compute an approximation of the second-order statistics of the channel estimation error which are required for accurate equalization. Second, a CNN-based demapper jointly processes a large number of orthogonal frequency-division multiplexing (OFDM) symbols and subcarriers, which allows it to compute better log likelihood ratios (LLRs) by compensating for channel aging. The resulting architecture can be used in the up- and downlink and is trained in an end-to-end manner, removing the need for hard-to-get perfect channel state information (CSI) during the training phase. Simulation results demonstrate consistent performance improvements over the baseline which are especially pronounced in high mobility scenarios." @default.
- W3113122707 created "2020-12-21" @default.
- W3113122707 creator A5038155303 @default.
- W3113122707 creator A5062167670 @default.
- W3113122707 creator A5074728359 @default.
- W3113122707 creator A5076265502 @default.
- W3113122707 date "2021-08-01" @default.
- W3113122707 modified "2023-10-17" @default.
- W3113122707 title "Machine Learning for MU-MIMO Receive Processing in OFDM Systems" @default.
- W3113122707 cites W2094655360 @default.
- W3113122707 cites W2103749601 @default.
- W3113122707 cites W2139317044 @default.
- W3113122707 cites W2734408173 @default.
- W3113122707 cites W2736068844 @default.
- W3113122707 cites W2738538347 @default.
- W3113122707 cites W2770606349 @default.
- W3113122707 cites W2793041733 @default.
- W3113122707 cites W2804075771 @default.
- W3113122707 cites W2893910439 @default.
- W3113122707 cites W2936900179 @default.
- W3113122707 cites W2963190722 @default.
- W3113122707 cites W2963408536 @default.
- W3113122707 cites W2964021722 @default.
- W3113122707 cites W2974170798 @default.
- W3113122707 cites W3011944543 @default.
- W3113122707 cites W3019763781 @default.
- W3113122707 cites W3031023929 @default.
- W3113122707 cites W3036589489 @default.
- W3113122707 cites W3097372264 @default.
- W3113122707 cites W3128021040 @default.
- W3113122707 cites W4211120851 @default.
- W3113122707 doi "https://doi.org/10.1109/jsac.2021.3087224" @default.
- W3113122707 hasPublicationYear "2021" @default.
- W3113122707 type Work @default.
- W3113122707 sameAs 3113122707 @default.
- W3113122707 citedByCount "14" @default.
- W3113122707 countsByYear W31131227072021 @default.
- W3113122707 countsByYear W31131227072022 @default.
- W3113122707 countsByYear W31131227072023 @default.
- W3113122707 crossrefType "journal-article" @default.
- W3113122707 hasAuthorship W3113122707A5038155303 @default.
- W3113122707 hasAuthorship W3113122707A5062167670 @default.
- W3113122707 hasAuthorship W3113122707A5074728359 @default.
- W3113122707 hasAuthorship W3113122707A5076265502 @default.
- W3113122707 hasBestOaLocation W31131227073 @default.
- W3113122707 hasConcept C105795698 @default.
- W3113122707 hasConcept C113775141 @default.
- W3113122707 hasConcept C11413529 @default.
- W3113122707 hasConcept C119857082 @default.
- W3113122707 hasConcept C127162648 @default.
- W3113122707 hasConcept C130946814 @default.
- W3113122707 hasConcept C138660444 @default.
- W3113122707 hasConcept C148063708 @default.
- W3113122707 hasConcept C154945302 @default.
- W3113122707 hasConcept C185429906 @default.
- W3113122707 hasConcept C207987634 @default.
- W3113122707 hasConcept C2781067378 @default.
- W3113122707 hasConcept C33923547 @default.
- W3113122707 hasConcept C40409654 @default.
- W3113122707 hasConcept C41008148 @default.
- W3113122707 hasConcept C555944384 @default.
- W3113122707 hasConcept C75755367 @default.
- W3113122707 hasConcept C76155785 @default.
- W3113122707 hasConcept C90652560 @default.
- W3113122707 hasConceptScore W3113122707C105795698 @default.
- W3113122707 hasConceptScore W3113122707C113775141 @default.
- W3113122707 hasConceptScore W3113122707C11413529 @default.
- W3113122707 hasConceptScore W3113122707C119857082 @default.
- W3113122707 hasConceptScore W3113122707C127162648 @default.
- W3113122707 hasConceptScore W3113122707C130946814 @default.
- W3113122707 hasConceptScore W3113122707C138660444 @default.
- W3113122707 hasConceptScore W3113122707C148063708 @default.
- W3113122707 hasConceptScore W3113122707C154945302 @default.
- W3113122707 hasConceptScore W3113122707C185429906 @default.
- W3113122707 hasConceptScore W3113122707C207987634 @default.
- W3113122707 hasConceptScore W3113122707C2781067378 @default.
- W3113122707 hasConceptScore W3113122707C33923547 @default.
- W3113122707 hasConceptScore W3113122707C40409654 @default.
- W3113122707 hasConceptScore W3113122707C41008148 @default.
- W3113122707 hasConceptScore W3113122707C555944384 @default.
- W3113122707 hasConceptScore W3113122707C75755367 @default.
- W3113122707 hasConceptScore W3113122707C76155785 @default.
- W3113122707 hasConceptScore W3113122707C90652560 @default.
- W3113122707 hasIssue "8" @default.
- W3113122707 hasLocation W31131227071 @default.
- W3113122707 hasLocation W31131227072 @default.
- W3113122707 hasLocation W31131227073 @default.
- W3113122707 hasLocation W31131227074 @default.
- W3113122707 hasOpenAccess W3113122707 @default.
- W3113122707 hasPrimaryLocation W31131227071 @default.
- W3113122707 hasRelatedWork W1551931186 @default.
- W3113122707 hasRelatedWork W1970868902 @default.
- W3113122707 hasRelatedWork W1985632374 @default.
- W3113122707 hasRelatedWork W2062416811 @default.
- W3113122707 hasRelatedWork W2062675820 @default.
- W3113122707 hasRelatedWork W2102394268 @default.
- W3113122707 hasRelatedWork W2352105133 @default.
- W3113122707 hasRelatedWork W2382010743 @default.