Online Radio Map Update Based on a Marginalized Particle Gaussian Process

In this paper, a novel scheme is reported to adapt radio maps to environmental dynamics in an online fashion by combining crowdsourcing and gaussian process regression (GPR). Specifically, a Marginalized Particle Gaussian Process (MPGP) is adopted to recursively fuse crowdsourced fingerprints with an existing offline radio map. The advantages of the proposed scheme lie in the efficiency and scalability in comparison with the traditional approaches. Extensive experiments are carried out in a real scenario of nearly 1000 m2 during five months, and a comparison is made with several existing popular solutions. It is shown that the proposed scheme outperforms its counterparts in terms of both robustness and accuracy.

[1]  Han Zou,et al.  Exploiting cyclic features of walking for pedestrian dead reckoning with unconstrained smartphones , 2016, UbiComp.

[2]  Wenbin Lin,et al.  Indoor Localization and Automatic Fingerprint Update with Altered AP Signals , 2017, IEEE Transactions on Mobile Computing.

[3]  Aboelmagd Noureldin,et al.  Dynamic Online-Calibrated Radio Maps for Indoor Positioning in Wireless Local Area Networks , 2013, IEEE Transactions on Mobile Computing.

[4]  Hailong Zhao,et al.  Applying kriging interpolation for WiFi fingerprinting based indoor positioning systems , 2016, 2016 IEEE Wireless Communications and Networking Conference.

[5]  Neil D. Lawrence,et al.  WiFi-SLAM Using Gaussian Process Latent Variable Models , 2007, IJCAI.

[6]  Andrew G. Dempster,et al.  Database updating through user feedback in fingerprint-based Wi-Fi location systems , 2010, 2010 Ubiquitous Positioning Indoor Navigation and Location Based Service.

[7]  Yunhao Liu,et al.  Locating in fingerprint space: wireless indoor localization with little human intervention , 2012, Mobicom '12.

[8]  Baoqi Huang,et al.  On the Performance Analysis of Wifi Based Localization , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Hao Jiang,et al.  A Robust Indoor Positioning System Based on the Procrustes Analysis and Weighted Extreme Learning Machine , 2016, IEEE Transactions on Wireless Communications.

[10]  Brahim Chaib-draa,et al.  A Marginalized Particle Gaussian Process Regression , 2012, NIPS.

[11]  Baoqi Huang,et al.  Dimension reduction in radio maps based on the supervised kernel principal component analysis , 2018, Soft Computing.

[12]  Baoqi Huang,et al.  An accurate step detection algorithm using unconstrained smartphones , 2015, The 27th Chinese Control and Decision Conference (2015 CCDC).

[13]  Yiqiang Chen,et al.  Adaptive Localization through Transfer Learning in Indoor Wi-Fi Environment , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[14]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[15]  Gi-Wan Yoon,et al.  Radio Map Update Automation for WiFi Positioning Systems , 2013, IEEE Communications Letters.

[16]  Anshul Rai,et al.  Zee: zero-effort crowdsourcing for indoor localization , 2012, Mobicom '12.

[17]  Baoqi Huang,et al.  A Novel Walking Detection and Step Counting Algorithm Using Unconstrained Smartphones , 2018, Sensors.

[18]  Hao Jiang,et al.  WinIPS: WiFi-Based Non-Intrusive Indoor Positioning System With Online Radio Map Construction and Adaptation , 2017, IEEE Transactions on Wireless Communications.

[19]  Chenshu Wu,et al.  Automatic Radio Map Adaptation for Indoor Localization Using Smartphones , 2018, IEEE Transactions on Mobile Computing.