Cover Image

Deep Learning-Aided Multicarrier Systems

This paper proposes a deep learning (DL)-aided multicarrier (MC) system operating on fading channels, where both modulation and demodulation blocks are modeled by deep neural networks (DNNs), regarded as the encoder and decoder of an autoencoder (AE) architecture, respectively. Unlike existing AE-ba...

Full description

Saved in:
Bibliographic Details
Main Author: Luong, Thien Van
Other Authors: Ko, Youngwook
Format: Article
Language:English
Published: IEEE Transactions on Wireless Communications 2021
Subjects:
Autoencoder
deep learning
deep neural network
DNN
Online Access:https://ieeexplore.ieee.org/document/9271932
https://dlib.phenikaa-uni.edu.vn/handle/PNK/1777
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-1777
record_format dspace
spelling oai:localhost:PNK-17772022-08-17T05:54:43Z Deep Learning-Aided Multicarrier Systems Luong, Thien Van Ko, Youngwook Matthaiou, Michail Ngo, Anh Vien Le, Minh-Tuan Ngo, Vu-Duc Autoencoder deep learning deep neural network DNN This paper proposes a deep learning (DL)-aided multicarrier (MC) system operating on fading channels, where both modulation and demodulation blocks are modeled by deep neural networks (DNNs), regarded as the encoder and decoder of an autoencoder (AE) architecture, respectively. Unlike existing AE-based systems, which incorporate domain knowledge of a channel equalizer to suppress the effects of wireless channels, the proposed scheme, termed as MC-AE, directly feeds the decoder with the channel state information and received signal, which are then processed in a fully data-driven manner. This new approach enables MC-AE to jointly learn the encoder and decoder to optimize the diversity and coding gains over fading channels. In particular, the block error rate of MC-AE is analyzed to show its higher performance gains than existing hand-crafted baselines, such as various recent index modulation-based MC schemes. We then extend MC-AE to multiuser scenarios, wherein the resultant system is termed as MU-MC-AE. Accordingly, two novel DNN structures for uplink and downlink MU-MC-AE transmissions are proposed, along with a novel cost function that ensures a fast training convergence and fairness among users. Finally, simulation results are provided to show the superiority of the proposed DL-based schemes over current baselines, in terms of both the error performance and receiver complexity. 2021-06-15T07:48:12Z 2021-06-15T07:48:12Z 2021 Article Working Paper https://ieeexplore.ieee.org/document/9271932 https://dlib.phenikaa-uni.edu.vn/handle/PNK/1777 10.1109/TWC.2020.3039180 en IEEE Transactions on Wireless Communications
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic Autoencoder
deep learning
deep neural network
DNN
spellingShingle Autoencoder
deep learning
deep neural network
DNN
Luong, Thien Van
Deep Learning-Aided Multicarrier Systems
description This paper proposes a deep learning (DL)-aided multicarrier (MC) system operating on fading channels, where both modulation and demodulation blocks are modeled by deep neural networks (DNNs), regarded as the encoder and decoder of an autoencoder (AE) architecture, respectively. Unlike existing AE-based systems, which incorporate domain knowledge of a channel equalizer to suppress the effects of wireless channels, the proposed scheme, termed as MC-AE, directly feeds the decoder with the channel state information and received signal, which are then processed in a fully data-driven manner. This new approach enables MC-AE to jointly learn the encoder and decoder to optimize the diversity and coding gains over fading channels. In particular, the block error rate of MC-AE is analyzed to show its higher performance gains than existing hand-crafted baselines, such as various recent index modulation-based MC schemes. We then extend MC-AE to multiuser scenarios, wherein the resultant system is termed as MU-MC-AE. Accordingly, two novel DNN structures for uplink and downlink MU-MC-AE transmissions are proposed, along with a novel cost function that ensures a fast training convergence and fairness among users. Finally, simulation results are provided to show the superiority of the proposed DL-based schemes over current baselines, in terms of both the error performance and receiver complexity.
author2 Ko, Youngwook
author_facet Ko, Youngwook
Luong, Thien Van
format Article
author Luong, Thien Van
author_sort Luong, Thien Van
title Deep Learning-Aided Multicarrier Systems
title_short Deep Learning-Aided Multicarrier Systems
title_full Deep Learning-Aided Multicarrier Systems
title_fullStr Deep Learning-Aided Multicarrier Systems
title_full_unstemmed Deep Learning-Aided Multicarrier Systems
title_sort deep learning-aided multicarrier systems
publisher IEEE Transactions on Wireless Communications
publishDate 2021
url https://ieeexplore.ieee.org/document/9271932
https://dlib.phenikaa-uni.edu.vn/handle/PNK/1777
_version_ 1751856252053356544
score 8.891053

Similar Items