WiFi fingerprint database updating based on surface fitting
TIAN Zengshan, DAI Haipeng
Institute of Wireless Location and Space Measurement, Chongqing Key Laboratory of Mobile Communications Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Abstract:To solve the problem that the fingerprint database updating requires a huge amount of time and laboring effort, a new Received Signal Strength (RSS) estimation method was proposed in WiFi environment. Part of remeasured RSS fingerprints was used to fit RSS surface by the radial basis function interpolation, the RSSs of the unknown reference points were estimated nearby the known reference points, and then the whole fingerprint database was update. The extensive experiments prove that only a quarter of the reference points need to be remeasured, the cumulative error probability will be similar with the actual database within the positioning error of 2 m, and thus the method guarantees the satisfactory positioning accuracy.
[1] 魏恒瑞, 王蔚庭. 基于WIFI定位技术的改进型位置指纹识别算法研究[J]. 制造业自动化, 2014, 36(23):148-151.(WEI H R, WANG W T. Modified position fingerprint identification algorithm based on WIFI positioning technology research[J]. Manufacturing Automation, 2014, 36(23):148-151.) [2] 赵爽. 复数神经网络在基于WiFi的室内LBS应用[J]. 大连工业大学学报, 2015, 34(4):300-303.(ZHAO S.Complex neural network application on indoor positioning LBS based on WiFi[J]. Journal of Dalian Polytechnic University, 2015, 34(4):300-303.) [3] TSUI A W, CHUANG Y H, CHU H H. Unsupervised learning for solving RSS hardware variance problem in WiFi localization[J]. Mobile Networks and Applications, 2009, 14(5):677-691. [4] KOWEERAWONG C, WIPUSITWARAKUN K, KAEMARUNGSI K. Indoor localization improvement via adaptive RSS fingerprinting database[C]//Proceedings of the 2013 International Conference on Information Networking. Piscataway, NJ:IEEE, 2013:412-416. [5] PENG L, HAN J, MENG W, et al. Research on radio-map construction in indoor WLAN positioning system[C]//Proceedings of the 20101st International Conference on Pervasive Computing Signal Processing and Applications. Piscataway, NJ:IEEE, 2010:1073-1077. [6] KAEMARUNGSI K, KRISHNAMURTHY P. Analysis of WLAN's received signal strength indication for indoor location fingerprinting[J]. Pervasive and Mobile Computing, 2012, 8(2):292-316. [7] XU C, TAO D, XU C. Multi-view learning with incomplete views[J]. IEEE Transactions on Image Processing, 2015, 24(12):5812-5825. [8] DUVALLET F, TEWS A D. WiFi position estimation in industrial environments using Gaussian processes[C]//Proceedings of the 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ:IEEE, 2008:2216-2221. BackgroundTIAN Zengshan, born in 1968, Ph. D., professor. His research interests include personal communications, satellite navigation, wireless localization, signal detection and estimation.DAI Haipeng, born in 1989, M. S. candidate. His research interests include computer networks, artificial intelligence, software engineering.