Matches in SemOpenAlex for { <https://semopenalex.org/work/W3130147695> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3130147695 abstract "We propose a unified multi-layer perceptron (MLP) network to select an appropriate multiple-input, multiple-output (MIMO) detector for high-order quadrature amplitude modulations (QAMs) such as 64-, 256-, and 1024-QAM. The network is trained to select a low-complexity detector dynamically for 64-, 256-, and 1024-QAM from a set of candidate detectors, while simultaneously maintaining a block error rate (BLER) close to the highest complexity candidate detector. We train the network on a combined data set collected under various environments such as multiple modulation orders, channel profiles, and signal-to-noise ratios. For offline training, a selective back-propagation method is proposed wherein samples of specific <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$M$</tex> -QAM are used to update modulation specific weights between the hidden layer and the output layer of the MLP network. The common weights between the input layer and the hidden layer are updated using all the samples in the data set. Thus, a single unified network can be deployed for multiple modulation orders together. The performance is evaluated with different channel profiles including channels for which the network was not trained. Simulation results show that the proposed algorithm maintains the BLER close to that of the most complex candidate detector even under un-trained channel profiles. The proposed algorithm also reduces the computational complexity of the MIMO detection block up to 10×." @default.
- W3130147695 created "2021-03-01" @default.
- W3130147695 creator A5034823139 @default.
- W3130147695 creator A5044969532 @default.
- W3130147695 creator A5056967242 @default.
- W3130147695 date "2020-12-01" @default.
- W3130147695 modified "2023-09-26" @default.
- W3130147695 title "MIMO Detector Selection for Multiple High-Order Modulations with Unified Neural Network" @default.
- W3130147695 cites W2112772743 @default.
- W3130147695 cites W2128548897 @default.
- W3130147695 cites W2149772057 @default.
- W3130147695 cites W2286612019 @default.
- W3130147695 cites W2510699190 @default.
- W3130147695 cites W2804075771 @default.
- W3130147695 cites W2962956060 @default.
- W3130147695 cites W3013338186 @default.
- W3130147695 doi "https://doi.org/10.1109/globecom42002.2020.9348081" @default.
- W3130147695 hasPublicationYear "2020" @default.
- W3130147695 type Work @default.
- W3130147695 sameAs 3130147695 @default.
- W3130147695 citedByCount "1" @default.
- W3130147695 countsByYear W31301476952021 @default.
- W3130147695 crossrefType "proceedings-article" @default.
- W3130147695 hasAuthorship W3130147695A5034823139 @default.
- W3130147695 hasAuthorship W3130147695A5044969532 @default.
- W3130147695 hasAuthorship W3130147695A5056967242 @default.
- W3130147695 hasConcept C11413529 @default.
- W3130147695 hasConcept C121332964 @default.
- W3130147695 hasConcept C123079801 @default.
- W3130147695 hasConcept C127162648 @default.
- W3130147695 hasConcept C127413603 @default.
- W3130147695 hasConcept C138660444 @default.
- W3130147695 hasConcept C154945302 @default.
- W3130147695 hasConcept C207987634 @default.
- W3130147695 hasConcept C24326235 @default.
- W3130147695 hasConcept C24890656 @default.
- W3130147695 hasConcept C2524010 @default.
- W3130147695 hasConcept C2776639698 @default.
- W3130147695 hasConcept C2777210771 @default.
- W3130147695 hasConcept C32409245 @default.
- W3130147695 hasConcept C33923547 @default.
- W3130147695 hasConcept C41008148 @default.
- W3130147695 hasConcept C50644808 @default.
- W3130147695 hasConcept C56296756 @default.
- W3130147695 hasConcept C59030546 @default.
- W3130147695 hasConcept C60908668 @default.
- W3130147695 hasConcept C76155785 @default.
- W3130147695 hasConcept C94915269 @default.
- W3130147695 hasConceptScore W3130147695C11413529 @default.
- W3130147695 hasConceptScore W3130147695C121332964 @default.
- W3130147695 hasConceptScore W3130147695C123079801 @default.
- W3130147695 hasConceptScore W3130147695C127162648 @default.
- W3130147695 hasConceptScore W3130147695C127413603 @default.
- W3130147695 hasConceptScore W3130147695C138660444 @default.
- W3130147695 hasConceptScore W3130147695C154945302 @default.
- W3130147695 hasConceptScore W3130147695C207987634 @default.
- W3130147695 hasConceptScore W3130147695C24326235 @default.
- W3130147695 hasConceptScore W3130147695C24890656 @default.
- W3130147695 hasConceptScore W3130147695C2524010 @default.
- W3130147695 hasConceptScore W3130147695C2776639698 @default.
- W3130147695 hasConceptScore W3130147695C2777210771 @default.
- W3130147695 hasConceptScore W3130147695C32409245 @default.
- W3130147695 hasConceptScore W3130147695C33923547 @default.
- W3130147695 hasConceptScore W3130147695C41008148 @default.
- W3130147695 hasConceptScore W3130147695C50644808 @default.
- W3130147695 hasConceptScore W3130147695C56296756 @default.
- W3130147695 hasConceptScore W3130147695C59030546 @default.
- W3130147695 hasConceptScore W3130147695C60908668 @default.
- W3130147695 hasConceptScore W3130147695C76155785 @default.
- W3130147695 hasConceptScore W3130147695C94915269 @default.
- W3130147695 hasLocation W31301476951 @default.
- W3130147695 hasOpenAccess W3130147695 @default.
- W3130147695 hasPrimaryLocation W31301476951 @default.
- W3130147695 hasRelatedWork W1543969223 @default.
- W3130147695 hasRelatedWork W2116498579 @default.
- W3130147695 hasRelatedWork W2117624092 @default.
- W3130147695 hasRelatedWork W2141579362 @default.
- W3130147695 hasRelatedWork W2143528646 @default.
- W3130147695 hasRelatedWork W2147200311 @default.
- W3130147695 hasRelatedWork W2319504435 @default.
- W3130147695 hasRelatedWork W2544069393 @default.
- W3130147695 hasRelatedWork W3100544904 @default.
- W3130147695 hasRelatedWork W2182239828 @default.
- W3130147695 isParatext "false" @default.
- W3130147695 isRetracted "false" @default.
- W3130147695 magId "3130147695" @default.
- W3130147695 workType "article" @default.