Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379382365> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4379382365 endingPage "16" @default.
- W4379382365 startingPage "1" @default.
- W4379382365 abstract "Terahertz ultra-massive MIMO (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless networks, for which channel estimation is highly challenging. Traditional analytical estimation methods are no longer effective, as the enlarged array aperture and the small wavelength result in a mixture of far-field and near-field paths, constituting a hybrid-field channel. Deep learning (DL)-based methods, despite the competitive performance, generally lack theoretical guarantees and scale poorly with the size of the array. In this paper, we propose a general DL framework for THz UM-MIMO channel estimation, which leverages existing iterative channel estimators and is with provable guarantees. Each iteration is implemented by a fixed point network (FPN), consisting of a closed-form linear estimator and a DL-based non-linear estimator. The proposed method perfectly matches the THz UM-MIMO channel estimation due to several unique advantages. First, the complexity is low and adaptive. It enjoys provable linear convergence with a low per-iteration cost and monotonically increasing accuracy, which enables an adaptive accuracy-complexity tradeoff. Second, it is robust to practical distribution shifts and can directly generalize to a variety of heavily out-of-distribution scenarios with almost no performance loss, which is suitable for the complicated THz channel conditions. For practical usage, the proposed framework is further extended to wideband THz UM-MIMO systems with beam squint effect. Theoretical analysis and extensive simulation results are provided to illustrate the advantages over the state-of-the-art methods in estimation accuracy, convergence rate, complexity, and robustness." @default.
- W4379382365 created "2023-06-06" @default.
- W4379382365 creator A5025467937 @default.
- W4379382365 creator A5028609226 @default.
- W4379382365 creator A5036213588 @default.
- W4379382365 creator A5043356063 @default.
- W4379382365 creator A5044818286 @default.
- W4379382365 creator A5060020916 @default.
- W4379382365 creator A5079052203 @default.
- W4379382365 date "2023-01-01" @default.
- W4379382365 modified "2023-10-02" @default.
- W4379382365 title "An Adaptive and Robust Deep Learning Framework for THz Ultra-Massive MIMO Channel Estimation" @default.
- W4379382365 doi "https://doi.org/10.1109/jstsp.2023.3282832" @default.
- W4379382365 hasPublicationYear "2023" @default.
- W4379382365 type Work @default.
- W4379382365 citedByCount "1" @default.
- W4379382365 countsByYear W43793823652023 @default.
- W4379382365 crossrefType "journal-article" @default.
- W4379382365 hasAuthorship W4379382365A5025467937 @default.
- W4379382365 hasAuthorship W4379382365A5028609226 @default.
- W4379382365 hasAuthorship W4379382365A5036213588 @default.
- W4379382365 hasAuthorship W4379382365A5043356063 @default.
- W4379382365 hasAuthorship W4379382365A5044818286 @default.
- W4379382365 hasAuthorship W4379382365A5060020916 @default.
- W4379382365 hasAuthorship W4379382365A5079052203 @default.
- W4379382365 hasBestOaLocation W43793823651 @default.
- W4379382365 hasConcept C105795698 @default.
- W4379382365 hasConcept C11413529 @default.
- W4379382365 hasConcept C126255220 @default.
- W4379382365 hasConcept C127162648 @default.
- W4379382365 hasConcept C148063708 @default.
- W4379382365 hasConcept C179799912 @default.
- W4379382365 hasConcept C185429906 @default.
- W4379382365 hasConcept C207987634 @default.
- W4379382365 hasConcept C33923547 @default.
- W4379382365 hasConcept C41008148 @default.
- W4379382365 hasConcept C555944384 @default.
- W4379382365 hasConcept C76155785 @default.
- W4379382365 hasConceptScore W4379382365C105795698 @default.
- W4379382365 hasConceptScore W4379382365C11413529 @default.
- W4379382365 hasConceptScore W4379382365C126255220 @default.
- W4379382365 hasConceptScore W4379382365C127162648 @default.
- W4379382365 hasConceptScore W4379382365C148063708 @default.
- W4379382365 hasConceptScore W4379382365C179799912 @default.
- W4379382365 hasConceptScore W4379382365C185429906 @default.
- W4379382365 hasConceptScore W4379382365C207987634 @default.
- W4379382365 hasConceptScore W4379382365C33923547 @default.
- W4379382365 hasConceptScore W4379382365C41008148 @default.
- W4379382365 hasConceptScore W4379382365C555944384 @default.
- W4379382365 hasConceptScore W4379382365C76155785 @default.
- W4379382365 hasFunder F4320321001 @default.
- W4379382365 hasLocation W43793823651 @default.
- W4379382365 hasLocation W43793823652 @default.
- W4379382365 hasLocation W43793823653 @default.
- W4379382365 hasOpenAccess W4379382365 @default.
- W4379382365 hasPrimaryLocation W43793823651 @default.
- W4379382365 hasRelatedWork W2137509205 @default.
- W4379382365 hasRelatedWork W2162261253 @default.
- W4379382365 hasRelatedWork W2166632935 @default.
- W4379382365 hasRelatedWork W2767299482 @default.
- W4379382365 hasRelatedWork W2884187557 @default.
- W4379382365 hasRelatedWork W2989639077 @default.
- W4379382365 hasRelatedWork W3004680695 @default.
- W4379382365 hasRelatedWork W3008958301 @default.
- W4379382365 hasRelatedWork W4316829721 @default.
- W4379382365 hasRelatedWork W2129498500 @default.
- W4379382365 isParatext "false" @default.
- W4379382365 isRetracted "false" @default.
- W4379382365 workType "article" @default.