Super-Resolution Channel Estimation Based on Deep Sampling Feedback Structure

  • Jinwei Ji
  • , Chunhui Liu*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A novel pilot-assisted channel estimation model, Matrix-DenseNet, is introduced, which has a unique matrix-like structure consisting of five rows and six columns. Dense connectivity is incorporated within each row to enhance feature propagation and reduce parameter count. Additionally, deep sampling paths and feature feedback paths are set up across columns, creating a deep sampling feedback structure that further improves the extraction of multi-resolution features from the initial CSI tensor. Simulation results demonstrate that the proposed Matrix-DenseNet significantly improves the normalized mean square error (NMSE) and bit error rate (BER) performance of OFDM systems in high-speed environments.

Original languageEnglish
Title of host publicationProceedings of the 4th International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2024 - Volume I
EditorsWeijian Liu, Qi Wang, Jinchao Feng, Wenli Zhang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages394-401
Number of pages8
ISBN (Print)9789819653133
DOIs
StatePublished - 2025
Event4th International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2024 - Beijing, China
Duration: 22 Jun 202425 Jun 2024

Publication series

NameLecture Notes in Electrical Engineering
Volume1413 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference4th International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2024
Country/TerritoryChina
CityBeijing
Period22/06/2425/06/24

Keywords

  • Channel estimation
  • Deep learning
  • OFDM
  • Super resolution

Fingerprint

Dive into the research topics of 'Super-Resolution Channel Estimation Based on Deep Sampling Feedback Structure'. Together they form a unique fingerprint.

Cite this