Edge Big Data-Enabled Low-Cost Indoor Localization Based on Bayesian Analysis of RSS

Indoor localization has attracted much attention recently, due to its wide applications in location-based services(LBSs). Localization accuracy and system costs are the key issues while designing indoor localization schemes. In this paper, an edge big data-enabled indoor localization scheme is proposed. We use the radio signal strength (RSS) information that is always available wherever WiFi coverage is available, to avoid the costs on deploying and maintaining specific devices for indoor localization. Bayesian theory and edge computing are adopted in our system, so that big localization data is collected and utilized to update the prior location probabilities. A testbed, BJUTLocate, is built to evaluate the performance of the proposed scheme, and the evaluation results show its significant performance improvement.

[1]  Yunhao Liu,et al.  Non-Invasive Detection of Moving and Stationary Human With WiFi , 2015, IEEE Journal on Selected Areas in Communications.

[2]  Yong Up Lee,et al.  Long-range indoor hybrid localization system design with visible light communications and wireless network , 2012, 2012 IEEE Photonics Society Summer Topical Meeting Series.

[3]  Haiyong Luo,et al.  An RSSI gradient-based AP localization algorithm , 2014, China Communications.

[4]  F. Richard Yu,et al.  Transport Control Strategies in Named Data Networking: A Survey , 2016, IEEE Communications Surveys & Tutorials.

[5]  Maxim Shchekotov,et al.  Indoor localization methods based on Wi-Fi lateration and signal strength data collection , 2015, 2015 17th Conference of Open Innovations Association (FRUCT).

[6]  Jie Yang,et al.  Accurate WiFi Based Localization for Smartphones Using Peer Assistance , 2014, IEEE Transactions on Mobile Computing.

[7]  Jianbin Hu,et al.  Radio Map Filter for Sensor Network Indoor Localization Systems , 2007, 2007 5th IEEE International Conference on Industrial Informatics.

[8]  Jiming Chen,et al.  Gradient-Based Fingerprinting for Indoor Localization and Tracking , 2016, IEEE Transactions on Industrial Electronics.

[9]  Heng Fan,et al.  The research and improvement of indoor localization algorithms based on RSSI , 2013, Proceedings of 2013 3rd International Conference on Computer Science and Network Technology.

[10]  Fabiola Colone,et al.  Parasitic Exploitation of Wi-Fi Signals for Indoor Radar Surveillance , 2015, IEEE Transactions on Vehicular Technology.

[11]  Kai-Tai Song,et al.  Location estimation using probability map of a ZigBee sensor network , 2013, 2013 International Conference on Advanced Robotics and Intelligent Systems.

[12]  Subrat Kar,et al.  Novel RSSI evaluation models for accurate indoor localization with sensor networks , 2014, 2014 Twentieth National Conference on Communications (NCC).

[13]  A. Singh,et al.  Real time RSSI error reduction in distance estimation using RLS algorithm , 2013, 2013 3rd IEEE International Advance Computing Conference (IACC).

[14]  Nital H. Mistry,et al.  RSSI Based Localization Scheme in Wireless Sensor Networks: A Survey , 2015, 2015 Fifth International Conference on Advanced Computing & Communication Technologies.

[15]  Thierry Val,et al.  BLE localization using RSSI measurements and iRingLA , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[16]  Yuguang Fang,et al.  Spectrum Management for Proactive Video Caching in Information-Centric Cognitive Radio Networks , 2016, IEEE Journal on Selected Areas in Communications.

[17]  Hung-Huan Liu,et al.  Study on the use of a weighted screening method for indoor positioning systems , 2012, The 15th International Symposium on Wireless Personal Multimedia Communications.