FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387244924> ?p ?o ?g. }

• W4387244924 abstract "<p>The article focuses on the problem of detecting transmitted data over an additive Gaussian noise channel. We propose an integration of various deep-learning architectures with the classical Viterbi algorithm for channel estimation and equalization, to improve the estimation performance.<br> The goal is to design communication schemes that are oblivious to the channel coefficients.</p> <p>The study utilizes various deep-learning architectures to address the challenges of signal detection and data reconstruction over AWGN channels in communication systems, by learning the log-likelihood ratio (LLR) /priors of the channel as a function of the channel memory. We draw inspiration from the ViterbiNetmodel-based architecture and explore the implementation of novel deep neural network (DNN) architectures for channel estimation. These architectures include Convolutional Neural Networks (CNN), Transformer Encoder, Residual Convolutional Networks as well as SIONNA (by Nvidia) architecture.</p> <p>The performance of these architectures was evaluated by bit-error-rate (BER) across different channel conditions by signal-noise-ratio (SNR). The results show an improvement of up to 1dB in signal-to-noise ratio performance in the moderate and high signal-to-noise ratio regions compared to previously proposed learning-based solutions. The experiments demonstrate the potential of DNN model-based architectures for symbol detection and channel equalization in communication systems.</p> <p>Our work details the methodology used in the experiments, including the details of the DNN architecture implementation, data-set generation, channel model, training process, evaluation metrics, and semi-supervised online training method. The experiments demonstrate the performance of the proposed architectures and compare them to the classical Viterbi algorithm (with known CSI RS) and online Viterbi-Net pervious deep-learning-based architecture.</p> <p>In conclusion, the article presents the integration of different model-based deep-learning architectures into the Viterbi algorithm for signal reconstruction of transmitted data over an additive Gaussian noise channel. The proposed architectures show promising results in improving the signal-to-noise ratio performance compared to existing learning-based solutions. These findings contribute to the advancement of communication systems and highlight the potential for further improvements in performance and robustness.</p>" @default.
• W4387244924 created "2023-10-03" @default.
• W4387244924 creator A5072571599 @default.
• W4387244924 creator A5092983612 @default.
• W4387244924 creator A5092983613 @default.
• W4387244924 date "2023-10-02" @default.
• W4387244924 modified "2023-10-03" @default.
• W4387244924 title "ViterbiNet Transformed" @default.
• W4387244924 doi "https://doi.org/10.36227/techrxiv.24224875.v1" @default.
• W4387244924 hasPublicationYear "2023" @default.
• W4387244924 type Work @default.
• W4387244924 citedByCount "0" @default.
• W4387244924 crossrefType "posted-content" @default.
• W4387244924 hasAuthorship W4387244924A5072571599 @default.
• W4387244924 hasAuthorship W4387244924A5092983612 @default.
• W4387244924 hasAuthorship W4387244924A5092983613 @default.
• W4387244924 hasBestOaLocation W43872449241 @default.
• W4387244924 hasConcept C108583219 @default.
• W4387244924 hasConcept C113775141 @default.
• W4387244924 hasConcept C11413529 @default.
• W4387244924 hasConcept C117379686 @default.
• W4387244924 hasConcept C127162648 @default.
• W4387244924 hasConcept C154945302 @default.
• W4387244924 hasConcept C157899210 @default.
• W4387244924 hasConcept C169334058 @default.
• W4387244924 hasConcept C28490314 @default.
• W4387244924 hasConcept C41008148 @default.
• W4387244924 hasConcept C56296756 @default.
• W4387244924 hasConcept C57273362 @default.
• W4387244924 hasConcept C60582962 @default.
• W4387244924 hasConcept C76155785 @default.
• W4387244924 hasConcept C81363708 @default.
• W4387244924 hasConceptScore W4387244924C108583219 @default.
• W4387244924 hasConceptScore W4387244924C113775141 @default.
• W4387244924 hasConceptScore W4387244924C11413529 @default.
• W4387244924 hasConceptScore W4387244924C117379686 @default.
• W4387244924 hasConceptScore W4387244924C127162648 @default.
• W4387244924 hasConceptScore W4387244924C154945302 @default.
• W4387244924 hasConceptScore W4387244924C157899210 @default.
• W4387244924 hasConceptScore W4387244924C169334058 @default.
• W4387244924 hasConceptScore W4387244924C28490314 @default.
• W4387244924 hasConceptScore W4387244924C41008148 @default.
• W4387244924 hasConceptScore W4387244924C56296756 @default.
• W4387244924 hasConceptScore W4387244924C57273362 @default.
• W4387244924 hasConceptScore W4387244924C60582962 @default.
• W4387244924 hasConceptScore W4387244924C76155785 @default.
• W4387244924 hasConceptScore W4387244924C81363708 @default.
• W4387244924 hasLocation W43872449241 @default.
• W4387244924 hasOpenAccess W4387244924 @default.
• W4387244924 hasPrimaryLocation W43872449241 @default.
• W4387244924 hasRelatedWork W120707411 @default.
• W4387244924 hasRelatedWork W1529976251 @default.
• W4387244924 hasRelatedWork W1561286871 @default.
• W4387244924 hasRelatedWork W2003314313 @default.
• W4387244924 hasRelatedWork W2121021195 @default.
• W4387244924 hasRelatedWork W2147640366 @default.
• W4387244924 hasRelatedWork W2151877774 @default.
• W4387244924 hasRelatedWork W2157840368 @default.
• W4387244924 hasRelatedWork W4328011717 @default.
• W4387244924 hasRelatedWork W865101327 @default.
• W4387244924 isParatext "false" @default.
• W4387244924 isRetracted "false" @default.
• W4387244924 workType "article" @default.