Skip to main navigation Skip to search Skip to main content

Indoor Location Algorithm Based on Migration PSO-ELM in the Absence of Training Sets

  • Yifan Wu
  • , Wenhao Wang*
  • , Jing Zhang
  • *Corresponding author for this work

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

Abstract

Ultra-wideband technology has its unique advantages and is widely used in indoor localization. UWB positioning methods based on machine learning can significantly improve localization accuracy. However, the algorithms are generally trained based on experimental data and indoor features, which is difficult to applicate in other indoor places in the absence of scene training sets. In this work, a migration localization scheme for particle swarm algorithm to optimize the extreme learning machine (Migration PSO-ELM) is presented. This positioning algorithm generates virtual training datasets to achieve accurate localization in new indoor places without experimental data. According to the simulation results, Migration PSO-ELM can maintain high accuracy and shorten the deployment time when applied in new scenes without training sets.

Original languageEnglish
Title of host publicationAdvances in Guidance, Navigation and Control - Proceedings of 2022 International Conference on Guidance, Navigation and Control
EditorsLiang Yan, Haibin Duan, Yimin Deng, Liang Yan
PublisherSpringer Science and Business Media Deutschland GmbH
Pages3864-3873
Number of pages10
ISBN (Print)9789811966125
DOIs
StatePublished - 2023
EventInternational Conference on Guidance, Navigation and Control, ICGNC 2022 - Harbin, China
Duration: 5 Aug 20227 Aug 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume845 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Guidance, Navigation and Control, ICGNC 2022
Country/TerritoryChina
CityHarbin
Period5/08/227/08/22

Keywords

  • Indoor localization
  • Particle swarm algorithm optimization limit learning machine
  • Ultra-wideband

Fingerprint

Dive into the research topics of 'Indoor Location Algorithm Based on Migration PSO-ELM in the Absence of Training Sets'. Together they form a unique fingerprint.

Cite this