GAN network for cross-domain channel estimation in the 5G communication system

Advanced signal processing algorithms and sophisticated device generation processes in wireless communication systems enable block-based wireless communication systems with good communication performance. However, as the individual modules are designed for different purposes and situations, it is...

Full description

Saved in:
Bibliographic Details
Main Author: Quan, Yeming
Other Authors: Teh Kah Chan
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/149449
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-149449
record_format dspace
spelling sg-ntu-dr.10356-1494492023-07-04T17:02:43Z GAN network for cross-domain channel estimation in the 5G communication system Quan, Yeming Teh Kah Chan School of Electrical and Electronic Engineering EKCTeh@ntu.edu.sg Engineering::Electrical and electronic engineering::Wireless communication systems Advanced signal processing algorithms and sophisticated device generation processes in wireless communication systems enable block-based wireless communication systems with good communication performance. However, as the individual modules are designed for different purposes and situations, it is easy to achieve optimal performance on a particular module, but difficult to optimize the whole system. Recently, due to the successful applications of deep learning in other fields, researchers have considered its application to communication systems in order to improve systems performance. In this report, random functions and channel models are used to generate training and test data. Deep learning-based autoencoders and decoders are used as replacements for the signal processing modules in conventional wireless communication systems. The channel distribution is modeled using conditional generative adversarial networks. Generative adversarial networks consist of two parts, a generator, and a discriminator. It aims to generate images similar to the target images by random sampling from the latent space. Using the real channel output as training data, we can model the channel distribution and build an end-to-end communication system with a structure of autoencoder - conditional generative adversarial network - decoder, which is based on deep neural networks. Simulation results show that the deep learning-based structure can achieve global optimality through an end-to-end loss function. Comparison with the theoretical BER curve also shows this to be a promising communication architecture. Keywords: Deep learning, deep neural network, autoencoder, conditional generative adversarial network. Master of Science (Communications Engineering) 2021-06-08T06:13:53Z 2021-06-08T06:13:53Z 2021 Thesis-Master by Coursework Quan, Y. (2021). GAN network for cross-domain channel estimation in the 5G communication system. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/149449 https://hdl.handle.net/10356/149449 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering::Wireless communication systems
spellingShingle Engineering::Electrical and electronic engineering::Wireless communication systems
Quan, Yeming
GAN network for cross-domain channel estimation in the 5G communication system
description Advanced signal processing algorithms and sophisticated device generation processes in wireless communication systems enable block-based wireless communication systems with good communication performance. However, as the individual modules are designed for different purposes and situations, it is easy to achieve optimal performance on a particular module, but difficult to optimize the whole system. Recently, due to the successful applications of deep learning in other fields, researchers have considered its application to communication systems in order to improve systems performance. In this report, random functions and channel models are used to generate training and test data. Deep learning-based autoencoders and decoders are used as replacements for the signal processing modules in conventional wireless communication systems. The channel distribution is modeled using conditional generative adversarial networks. Generative adversarial networks consist of two parts, a generator, and a discriminator. It aims to generate images similar to the target images by random sampling from the latent space. Using the real channel output as training data, we can model the channel distribution and build an end-to-end communication system with a structure of autoencoder - conditional generative adversarial network - decoder, which is based on deep neural networks. Simulation results show that the deep learning-based structure can achieve global optimality through an end-to-end loss function. Comparison with the theoretical BER curve also shows this to be a promising communication architecture. Keywords: Deep learning, deep neural network, autoencoder, conditional generative adversarial network.
author2 Teh Kah Chan
author_facet Teh Kah Chan
Quan, Yeming
format Thesis-Master by Coursework
author Quan, Yeming
author_sort Quan, Yeming
title GAN network for cross-domain channel estimation in the 5G communication system
title_short GAN network for cross-domain channel estimation in the 5G communication system
title_full GAN network for cross-domain channel estimation in the 5G communication system
title_fullStr GAN network for cross-domain channel estimation in the 5G communication system
title_full_unstemmed GAN network for cross-domain channel estimation in the 5G communication system
title_sort gan network for cross-domain channel estimation in the 5g communication system
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/149449
_version_ 1772826973884645376