Neural Network MIMO Detection for Coded Wireless Communication with Impairments

Omer Sholev, Haim H. Permuter, Eilam Ben-Dror, Wenliang Liang

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

5 Scopus citations

Abstract

In this paper, a neural network based Multiple-Input-Multiple-Output (MIMO) algorithm is presented. The algorithm is specifically designed to be integrated in a coded MIMO-OFDM system, and is based upon projected gradient descent iterations. We combine our model as a part of a modern coded MIMO-OFDM system, and we compare its performance with common MIMO detectors on simulated data, as well as on field data. We also investigated our model's performance in the presence of several common communication impairments, and demonstrated empirically its robustness. We show empirically that a single trained model is suited for the detection of both coded and uncoded data, with or without impairments, and in the presence of a wide range of tested SNR levels.

Original languageEnglish
Title of host publication2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)9781728131061
DOIs
StatePublished - 1 May 2020
Event2020 IEEE Wireless Communications and Networking Conference, WCNC 2020 - Seoul, Korea, Republic of
Duration: 25 May 202028 May 2020

Publication series

NameIEEE Wireless Communications and Networking Conference, WCNC
Volume2020-May
ISSN (Print)1525-3511

Conference

Conference2020 IEEE Wireless Communications and Networking Conference, WCNC 2020
Country/TerritoryKorea, Republic of
CitySeoul
Period25/05/2028/05/20

Keywords

  • Deep Learning
  • LDPC
  • MIMO-detection
  • impairments
  • iterative neural network
  • soft-decision
  • wireless communications

ASJC Scopus subject areas

  • Engineering (all)

Fingerprint

Dive into the research topics of 'Neural Network MIMO Detection for Coded Wireless Communication with Impairments'. Together they form a unique fingerprint.

Cite this