Deep learning based channel covariance matrix estimation with scene images

Weihua Xu, Feifei Gao, Jianhua Zhang, Xiaoming Tao, Ahmed Alkhateeb, Shaodan Ma

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

Abstract

Channel covariance matrix (CCM) is one critical parameter for designing the communications systems. In this paper, a novel framework of the deep learning (DL) based CCM estimation is proposed that exploits the perception of the transmission environment without any channel sample or the pilot signals. Specifically, as CCM is affected by the user's movement, we design a deep neural network (DNN) to predict CCM from the environmental images and user speed, where the environmental images can reflect the user location information. Simulation results show that the proposed method is effective and will benefit the subsequent channel estimation.

Original languageEnglish (US)
Title of host publication2021 IEEE/CIC International Conference on Communications in China, ICCC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages162-166
Number of pages5
ISBN (Electronic)9781665443852
DOIs
StatePublished - Jul 28 2021
Externally publishedYes
Event2021 IEEE/CIC International Conference on Communications in China, ICCC 2021 - Xiamen, China
Duration: Jul 28 2021Jul 30 2021

Publication series

Name2021 IEEE/CIC International Conference on Communications in China, ICCC 2021

Conference

Conference2021 IEEE/CIC International Conference on Communications in China, ICCC 2021
Country/TerritoryChina
CityXiamen
Period7/28/217/30/21

Keywords

  • Covariance estimation
  • Deep learning
  • Pilot free
  • Scene image

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Instrumentation

Fingerprint

Dive into the research topics of 'Deep learning based channel covariance matrix estimation with scene images'. Together they form a unique fingerprint.

Cite this