Diffusion PSO-LMS Adaptation over Networks

Sameer H. Arastu, Naveed Iqbal, Muhammad O. Bin Saeed, Azzedine Zerguine

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

2 Scopus citations

Abstract

A hybrid diffusion scheme, PSO-LMS, combining a particle swarm optimization (PSO) strategy and the least-mean square (LMS) algorithm, is developed here to optimize cost functions in a cooperative manner over networks, with a specific focus on channel estimation. The PSO component, through its built-in diffusion process, enhances the proposed scheme's ability to quickly locate the region containing the global minimum, thus enabling the LMS to take over and exploit both the temporal and spatial diversity of the data so as to quickly hone in on the global minimum. Simulation results illustrate the improved performance of this hybrid scheme over both non-cooperative and other hybrid strategies.

Original languageEnglish
Title of host publicationConference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages1538-1541
Number of pages4
ISBN (Electronic)9780738131269
DOIs
StatePublished - 1 Nov 2020

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2020-November
ISSN (Print)1058-6393

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

  • LMS
  • diffusion adaptation
  • network
  • particle swarm optimization

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Diffusion PSO-LMS Adaptation over Networks'. Together they form a unique fingerprint.

Cite this