An Efficient Radio Map Updating Algorithm based on K-Means and Gaussian Process Regression

Jianli Zhao, Xiang Gao, Xin Wang, Chunxiu Li, Min Song, Qiuxia Sun

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

Fingerprint-based indoor localisation suffers from influences such as fingerprint pre-collection, environment changes and expending a lot of manpower and time to update the radio map. To solve the problem, we propose an efficient radio map updating algorithm based on K-Means and Gaussian Process Regression (KMGPR). The algorithm builds a Gaussian Process Regression (GPR) predictive model based on a Gaussian mean function and realises the update of the radio map using K-Means. We have conducted experiments to evaluate the performance of the proposed algorithm and results show that GPR using the Gaussian mean function improves localisation accuracy by about 13·76% compared with other functions and KMGPR can reduce the computational complexity by about 7% to 20% with no obvious effects on accuracy.

Original languageEnglish
Pages (from-to)1055-1068
Number of pages14
JournalJournal of Navigation
Volume71
Issue number5
DOIs
StatePublished - 1 Sep 2018

Keywords

  • GPR
  • Indoor localisation
  • Machine learning
  • Radio Map updating

Fingerprint

Dive into the research topics of 'An Efficient Radio Map Updating Algorithm based on K-Means and Gaussian Process Regression'. Together they form a unique fingerprint.

Cite this