An Efficient Radio Map Updating Algorithm based on K-Means and Gaussian Process Regression. (30th April 2018)

• Record Type: Journal Article
• Authors: Zhao, Jianli; Gao, Xiang; Wang, Xin; Li, Chunxiu; Song, Min; Sun, Qiuxia
• Is Part Of: Journal of navigation. Volume 71:Number 5(2018)
• Page Start: 1055
• Page End: 1068
• Publication Date: 2018-04-30
• Subjects: Indoor localisation, -- Radio Map updating, -- GPR, -- Machine learning; Navigation -- Periodicals; 623.8905
• DOI: 10.1017/S037346331800019X
• Languages: English
• ISSNs: 0373-4633

Abstract

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.