Machine Learning-based MIMO Signal Detection in Wireless Networks with Random Traffic

Po Yen Lai, Rung Hung Gau

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

Abstract

In this paper, we propose a novel machine learning-based signal detection scheme for multi-user wireless multiple-input multiple-output (MIMO) networks with random traffic. We focus on the challenging case in which the number of active users that transmit data to the base station in a time slot is a random variable from the viewpoint of the base station. Instead of using multiple machine learning models and exhaustive search, we propose using a novel deep machine learning model that adopts an extended constellation diagram and a loss function based on the nonuniform probability mass function for transmitted symbols. Simulation results reveal that the proposed machine learning-based signal detection scheme outperforms the zero-forcing detector and the minimum mean square error detector in wireless MIMO networks when the number of active users is random.

Original languageEnglish
Title of host publication2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2298-2303
Number of pages6
ISBN (Electronic)9781665442664
DOIs
StatePublished - 2022
Event2022 IEEE Wireless Communications and Networking Conference, WCNC 2022 - Austin, United States
Duration: 10 Apr 202213 Apr 2022

Publication series

NameIEEE Wireless Communications and Networking Conference, WCNC
Volume2022-April
ISSN (Print)1525-3511

Conference

Conference2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
Country/TerritoryUnited States
CityAustin
Period10/04/2213/04/22

Keywords

  • Multiple-input multiple-output
  • deep neural networks
  • machine learning
  • prior probability
  • random traffic
  • signal detection
  • wireless communications

Fingerprint

Dive into the research topics of 'Machine Learning-based MIMO Signal Detection in Wireless Networks with Random Traffic'. Together they form a unique fingerprint.

Cite this