Performance evaluations of channel estimation using deep-learning based super-resolution

Daiki Maruyama, Kenji Kanai, Jiro Katto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Thanks to breakthrough and evolution of deep learning in computer vision areas, adaptation of deep learning into communication systems are getting lots of attention to researchers. Recently, a channel estimation method by using a deep learning-based image super-resolution (SR) technique, namely ChannelNet, has been proposed. Inspired by this research, in this paper, we propose a deep SR based channel estimation method by applying more accurate deep learning-based SR network architecture, EDSR. In order to enhance intelligibility and reliability of deep SR based channel estimation methods, we evaluate the performance of several deep SR based channel estimation methods (SRCNN, ChannelNet and EDSR) by carrying out practical 5G simulations. From the evaluations, the results conclude that the deep SR based channel estimation methods can potentially improve accuracy of channel estimation and reduce BER characteristics.

Original languageEnglish
Title of host publication2021 IEEE 18th Annual Consumer Communications and Networking Conference, CCNC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728197944
DOIs
Publication statusPublished - 2021 Jan 9
Event18th IEEE Annual Consumer Communications and Networking Conference, CCNC 2021 - Virtual, Las Vegas, United States
Duration: 2021 Jan 92021 Jan 13

Publication series

Name2021 IEEE 18th Annual Consumer Communications and Networking Conference, CCNC 2021

Conference

Conference18th IEEE Annual Consumer Communications and Networking Conference, CCNC 2021
CountryUnited States
CityVirtual, Las Vegas
Period21/1/921/1/13

Keywords

  • 5g system
  • Channel estimation
  • Deep learning
  • Physical layer
  • Super-resolution

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Performance evaluations of channel estimation using deep-learning based super-resolution'. Together they form a unique fingerprint.

Cite this