TY - JOUR
T1 - An Efficient Radio Map Updating Algorithm based on K-Means and Gaussian Process Regression
AU - Zhao, Jianli
AU - Gao, Xiang
AU - Wang, Xin
AU - Li, Chunxiu
AU - Song, Min
AU - Sun, Qiuxia
N1 - Publisher Copyright:
© 2018 The Royal Institute of Navigation.
PY - 2018/9/1
Y1 - 2018/9/1
N2 - 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.
AB - 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.
KW - GPR
KW - Indoor localisation
KW - Machine learning
KW - Radio Map updating
UR - http://www.scopus.com/inward/record.url?scp=85046091008&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046091008&partnerID=8YFLogxK
U2 - 10.1017/S037346331800019X
DO - 10.1017/S037346331800019X
M3 - Article
AN - SCOPUS:85046091008
SN - 0373-4633
VL - 71
SP - 1055
EP - 1068
JO - Journal of Navigation
JF - Journal of Navigation
IS - 5
ER -