FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313150549> ?p ?o ?g. }

• W4313150549 endingPage "573" @default.
• W4313150549 startingPage "557" @default.
• W4313150549 abstract "Future wireless systems are trending towards higher carrier frequencies that offer larger communication bandwidth but necessitate the use of large antenna arrays. Signal processing techniques for channel estimation currently deployed in wireless devices do not scale well to this “high-dimensional regime in terms of performance and pilot overhead. Meanwhile, training deep learning-based approaches for channel estimation requires large labeled datasets mapping pilot measurements to clean channel realizations, which can only be generated offline using simulated channels. In this paper, we develop a novel unsupervised over-the-air (OTA) algorithm that utilizes noisy received pilot measurements to train a deep generative model to output beamspace MIMO channel realizations. Our approach leverages Generative Adversarial Networks (GAN), while using a conditional input to distinguish between Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) channel realizations. We also present a federated implementation of the OTA algorithm that distributes the GAN training over multiple users and greatly reduces the user side computation. We then formulate channel estimation from a limited number of pilot measurements as an inverse problem and reconstruct the channel by optimizing the input vector of the trained generative model. Our proposed approach significantly outperforms Orthogonal Matching Pursuit on both LOS and NLOS channel models, and EM-GM-AMP – an Approximate Message Passing algorithm – on LOS channel models, while achieving comparable performance on NLOS channel models in terms of the normalized channel reconstruction error. More importantly, our proposed framework has the potential to be trained online using real noisy pilot measurements, is not restricted to a specific channel model and can even be utilized for a federated OTA design of a dataset generator from noisy data." @default.
• W4313150549 created "2023-01-06" @default.
• W4313150549 creator A5042833857 @default.
• W4313150549 creator A5061685202 @default.
• W4313150549 creator A5066254566 @default.
• W4313150549 date "2022-09-01" @default.
• W4313150549 modified "2023-10-16" @default.
• W4313150549 title "Over-the-Air Design of GAN Training for mmWave MIMO Channel Estimation" @default.
• W4313150549 cites W1632803383 @default.
• W4313150549 cites W1932847118 @default.
• W4313150549 cites W2026933032 @default.
• W4313150549 cites W2044762091 @default.
• W4313150549 cites W2060393849 @default.
• W4313150549 cites W2097323375 @default.
• W4313150549 cites W2111953900 @default.
• W4313150549 cites W2137628444 @default.
• W4313150549 cites W2147035723 @default.
• W4313150549 cites W2161741659 @default.
• W4313150549 cites W2166670884 @default.
• W4313150549 cites W2195833401 @default.
• W4313150549 cites W2278865433 @default.
• W4313150549 cites W2559695533 @default.
• W4313150549 cites W2770606349 @default.
• W4313150549 cites W2786277362 @default.
• W4313150549 cites W2790721964 @default.
• W4313150549 cites W2805022829 @default.
• W4313150549 cites W2899730059 @default.
• W4313150549 cites W2936900179 @default.
• W4313150549 cites W2938113616 @default.
• W4313150549 cites W2941806810 @default.
• W4313150549 cites W2945463326 @default.
• W4313150549 cites W2955897898 @default.
• W4313150549 cites W2962964572 @default.
• W4313150549 cites W2963290405 @default.
• W4313150549 cites W2964324349 @default.
• W4313150549 cites W2977090839 @default.
• W4313150549 cites W3015740919 @default.
• W4313150549 cites W3021094251 @default.
• W4313150549 cites W3047474013 @default.
• W4313150549 cites W3047506756 @default.
• W4313150549 cites W3097372264 @default.
• W4313150549 cites W3111067891 @default.
• W4313150549 cites W3120429547 @default.
• W4313150549 cites W3128163981 @default.
• W4313150549 cites W3129300348 @default.
• W4313150549 cites W3162286130 @default.
• W4313150549 cites W4210521031 @default.
• W4313150549 cites W4290996369 @default.
• W4313150549 doi "https://doi.org/10.1109/jsait.2022.3222479" @default.
• W4313150549 hasPublicationYear "2022" @default.
• W4313150549 type Work @default.
• W4313150549 citedByCount "1" @default.
• W4313150549 countsByYear W43131505492023 @default.
• W4313150549 crossrefType "journal-article" @default.
• W4313150549 hasAuthorship W4313150549A5042833857 @default.
• W4313150549 hasAuthorship W4313150549A5061685202 @default.
• W4313150549 hasAuthorship W4313150549A5066254566 @default.
• W4313150549 hasBestOaLocation W43131505492 @default.
• W4313150549 hasConcept C111919701 @default.
• W4313150549 hasConcept C113775141 @default.
• W4313150549 hasConcept C11413529 @default.
• W4313150549 hasConcept C127162648 @default.
• W4313150549 hasConcept C154910267 @default.
• W4313150549 hasConcept C154945302 @default.
• W4313150549 hasConcept C207987634 @default.
• W4313150549 hasConcept C2776257435 @default.
• W4313150549 hasConcept C2779960059 @default.
• W4313150549 hasConcept C31258907 @default.
• W4313150549 hasConcept C41008148 @default.
• W4313150549 hasConcept C555944384 @default.
• W4313150549 hasConcept C76155785 @default.
• W4313150549 hasConcept C97931131 @default.
• W4313150549 hasConceptScore W4313150549C111919701 @default.
• W4313150549 hasConceptScore W4313150549C113775141 @default.
• W4313150549 hasConceptScore W4313150549C11413529 @default.
• W4313150549 hasConceptScore W4313150549C127162648 @default.
• W4313150549 hasConceptScore W4313150549C154910267 @default.
• W4313150549 hasConceptScore W4313150549C154945302 @default.
• W4313150549 hasConceptScore W4313150549C207987634 @default.
• W4313150549 hasConceptScore W4313150549C2776257435 @default.
• W4313150549 hasConceptScore W4313150549C2779960059 @default.
• W4313150549 hasConceptScore W4313150549C31258907 @default.
• W4313150549 hasConceptScore W4313150549C41008148 @default.
• W4313150549 hasConceptScore W4313150549C555944384 @default.
• W4313150549 hasConceptScore W4313150549C76155785 @default.
• W4313150549 hasConceptScore W4313150549C97931131 @default.
• W4313150549 hasFunder F4320306076 @default.
• W4313150549 hasFunder F4320308258 @default.
• W4313150549 hasFunder F4320309480 @default.
• W4313150549 hasIssue "3" @default.
• W4313150549 hasLocation W43131505491 @default.
• W4313150549 hasLocation W43131505492 @default.
• W4313150549 hasOpenAccess W4313150549 @default.
• W4313150549 hasPrimaryLocation W43131505491 @default.
• W4313150549 hasRelatedWork W2159459930 @default.
• W4313150549 hasRelatedWork W2793383610 @default.
• W4313150549 hasRelatedWork W3004680695 @default.
• W4313150549 hasRelatedWork W3169811957 @default.

• next