Fingerprinting Positioning Algorithm for WiFi Based on Locally Weighted Regression and Support Vector Regression Optimized by Artificial Bee Colony

doi:10.16182/j.issn1004731x.joss.201706005

Abstract

Abstract: Since the traditional location fingerprinting algorithms have poor positioning accuracy and cost laborious efforts constructing fingerprinting database during the offline phase, a novel LWR-ABCSVR positioning algorithm was proposed, that the derived algorithm was based on the locally weighted regression (LWR) method and support vector regression was optimized by artificial bee colony (ABCSVR) algorithm. By using the proposed algorithm, the fingerprinting database was expanded by LWR step. The ABCSVR algorithm was employed to build the nonlinear relationship between the RSS values of reference points and their locations. The position of mobile terminal was predicted by the constructed model. Simulation results indicate that the proposed algorithm performs better than traditional location fingerprinting algorithms, in terms of positioning accuracy and database constructing costs.

Key words: WiFi, LWR algorithm, ABC algorithm, SVR algorithm, positioning technique

CLC Number:

TP391.9

Wang Yan, Yin Fucheng, Ji Zhicheng, Yan Dahu. Fingerprinting Positioning Algorithm for WiFi Based on Locally Weighted Regression and Support Vector Regression Optimized by Artificial Bee Colony[J]. Journal of System Simulation, 2017, 29(6): 1193-1200.

References

[1] Chen X, Pang J.Protecting query privacy in location- based services[J]. Geoinformatica (S1384-6175), 2012, 18(1): 95-133.
[2] Xifeng Liu, Yunbin Yuan.Model analysis method (MAM) on the effect of the second-order ionospheric delay on GPS positioning solution[J]. Chinese Science Bulletin (S1001-6538), 2010, 55(15): 1529-1534.
[3] Liu R P, Hedley M, Yang X.WLAN Location Service with TXOP[J]. IEEE Transactions on Computers (S0018-9340), 2013, 62(3): 589-598.
[4] Bahl P, Padmanabhan V N.RADAR: An In-Building RF-based User Location and Tracking System[J]. Institute of Electrical & Electronics Engineers Inc (S0160-8347), 2000, 2(1): 775-784.
[5] 石雪军, 纪志成. 基于射频识别的室内定位系统算法研究[J]. 系统仿真学报, 2015, 27(6): 1294-1300.
(Shi Xuejun, Ji Zhicheng.Indoor Positioning System Algorithm Based on RFID[J]. Journal of System Simulation (S1004-731X), 2015, 27(6): 1294-1300.)
[6] 孙继平, 李晨鑫. 基于WiFi和计时误差抑制的TOA煤矿井下目标定位方法[J]. 煤炭学报, 2014, 39(1): 192-197.
(Sun Jiping, Li Chenxin.TOA underground coal mine target positioning method based on WiFi and timing error suppression[J]. Journal of China Coal Society (S0253-9993), 2014, 39(1): 192-197.)
[7] Mok E, Cheung B K S. An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning[J]. ISPRS International Journal of Geo-Information (S2220-9964), 2013, 2(3): 854-868.
[8] 邓志安, 徐玉滨. 基于支持向量机回归算法的WLAN室内定位系统[J]. 仪器仪表学报, 2009, 30(6): 578-582.
(Deng Zhian, Xu Yubin.A Support Vector Regression Algorithm for Indoor Positioning in Wireless Local Area Networks[J]. Chinese Journal of Scientific Instrument (S0254-3087), 2009, 30(6): 578-582.)
[9] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 32-42.
(Zhang Xuegong.Introduction to Statistical Learning Theory and Support Vector Machines[J]. Acta Automatica Sinica (S0254-4156), 2000, 26(1): 32-42.)
[10] 邓志安. 基于学习算法的WLAN室内定位技术研究 [D]. 哈尔滨: 哈尔滨工业大学, 2012.
(Deng Zhian.Research on Learning Based WLAN Indoor Positioning Techniques [D]. Harbin, China: Harbin Institute of Technology, 2012.)
[11] 徐玉滨, 邓志安, 马琳. 基于核直接判别分析和支持向量回归的WLAN室内定位算法[J]. 电子与信息学报, 2011, 33(4): 896-901.
(Xu Yubin, Deng Zhian, Ma Lin.WLAN Indoor Positioning Algorithm Based on KDDA and SVR[J]. Journal of Electronics & Information Technology (S1009-5896), 2011, 33(4): 896-901.)
[12] 刘路, 王太勇. 基于人工蜂群算法的支持向量机优化[J]. 天津大学学报(自然科学与工程技术版), 2011, 44(9): 803-809.
(Liu Lu, Wang Tai-yong.Support Vector Machine Optimization Based on Artificial Bee Colony Algorithm[J]. Journal of Tianjin University (Science and Technology)(S0493-2137), 2011, 44(9): 803-809.)
[13] 张勇, 黄杰, 徐科宇. 基于PCA-LSSVR算法的WLAN室内定位方法[J]. 仪器仪表学报, 2015, 36(2): 408-414.
(Zhang Yong, Huang Jie, Xu Keyu.Indoor positioning algorithm for WLAN based on principal component analysis and least square support vector regression[J]. Chinese Journal of Scientific Instrument (S0254-3087), 2015, 36(2): 408-414.)
[14] 纪昌明, 周婷, 向腾飞, 等. 基于网格搜索和交叉验证的支持向量机在梯级水电系统隐随机调度中的应用[J]. 电力自动化设备, 2014, 34(3): 125-131.
(Ji Changming, Zhou Ting, Xiang Tengfei, et al.Application of support vector machine based on grid search and cross validation in implicit stochastic dispatch of cascaded hydropower stations[J]. Electric Power Automation Equipment (S1006-6047), 2014, 34(3): 125-131.)
[15] Karaboga D.An Idea Based on Honey Bee Swarm for Numerical Optimization [R]. Technical Eporttr06. Turkey: Computer Engineering Department, Engineering Faculty, Erciyes University, 2005.
[16] Hossain A K M M, Van H N, Jin Y, et al. Indoor Localization Using Multiple Wireless Technologies[C]// Mobile Adhoc and Sensor Systems, 2007. MASS: IEEE International Conference. USA: IEEE, 2007: 1-8.
[17] Du Y, Yang D, Xiu C.A Novel Method for Constructing a WIFI Positioning System with Efficient Manpower[J]. Sensors (S1424-8220), 2015, 15(4): 8358-8381.
[18] William S Cleveland, Susan J Devlin.Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting[J]. Journal of the American Statistical Association (S0162-1459), 1988, 83(403): 569-610.
[19] Jekabsons G, Kairish V, Zuravlyov V.An Analysis of Wi-Fi Based Indoor Positioning Accuracy[J]. Scientific Journal of Riga Technical University Computer Sciences (S1407-7493), 2012, 44(1): 131-137.
[20] Chang C C, Lin C J.LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems & Technology (S2231-1961), 2011, 2(3): 389-396.