[1]康晓非,李梦梦,乔 威.基于WiFi指纹的高精度室内定位融合算法[J].西安科技大学学报,2020,(03):470-476.[doi:10.13800/j.cnki.xakjdxxb.2020.0313]
 KANG Xiao-fei,LI Meng-meng,QIAO Wei.High-precision indoor localization fusion algorithm based on WiFi fingerprint[J].Journal of Xi'an University of Science and Technology,2020,(03):470-476.[doi:10.13800/j.cnki.xakjdxxb.2020.0313]
点击复制

基于WiFi指纹的高精度室内定位融合算法(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2020年03期
页码:
470-476
栏目:
出版日期:
2020-05-15

文章信息/Info

Title:
High-precision indoor localization fusion algorithm based on WiFi fingerprint
文章编号:
1672-9315(2020)03-0470-07
作者:
康晓非李梦梦乔 威
(西安科技大学 通信与信息工程学院,陕西 西安 710054)
Author(s):
KANG Xiao-feiLI Meng-mengQIAO Wei
(College of Communication and Information Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)
关键词:
室内定位 WiFi指纹 梯度提升决策树 粒子滤波 融合算法
Keywords:
indoor localization WiFi fingerprint gradient boosting decision tree(GBDT) particle filter(PF) fusion algorithm
分类号:
TN 92
DOI:
10.13800/j.cnki.xakjdxxb.2020.0313
文献标志码:
A
摘要:
针对室内环境中指纹定位接收信号强度信息的高维时变特性以及动态目标定位误差的累积问题,提出了一种基于梯度提升决策树与粒子滤波相结合的融合算法。该算法首先利用梯度提升决策树算法建立的位置坐标与接收信号强度之间的非线性映射模型,对在线接收的信号强度数据进行特征分类判别,实现位置的初步估计; 随着目标的运动,进一步结合粒子滤波方法,迭代地实现动态目标位置的精确预测; 另外,将定位轨迹与实际轨迹进行对比,以验证该算法的稳定性。实验仿真结果表明:累积分布函数在80%的百分位处,提出算法的定位精度控制在1.19 m以内,明显优于基于支持向量机、随机森林等定位算法; 同时较基于梯度提升决策树算法的定位精度提升了34.9%; 所获得的定位轨迹与实际轨迹的趋势一致且趋于收敛。
Abstract:
Aiming at the high-dimensional time-varying characteristics of received signal strength information for fingerprint positioning and the accumulation of dynamic target positioning errors in the indoor environment,a fusion algorithmis proposedbased on gradient boosting decision tree and particle filter.Firstly,the initial estimation of the position was achieved,using the nonlinear mapping model between the position coordinates and the received signal strength established by the gradient boosting decision tree algorithm to classify and discriminate the received signal strength data; then,with the movement of the target,the accurate prediction of the dynamic target position was iteratively realized in combination with the particle filtering method; in addition,a comparison of the positioning trajectory with the actual trajectory was made to verify the stability of the algorithm.The experimental results show that 80% of the proposed algorithms'positioning accuracy is controlled within 1.19 m,which is significantly better than the support vector machine and the random forest based positioning algorithm,and has increased by 34.9% in performance over the gradient boosting decision tree algorithms'positioning accuracy; the positioning trajectory also coincides with the trend of the actual trajectory and gradually converges.

参考文献/References:

[1] Tahat A,Kaddoum G,Yousefi S, et al.A look at the recent wireless positioning techniques with a focus on algorithms for moving receivers[J].IEEE Access,2016(4):6652-6680. [2]Zhu H,Liu F,Li H.Efficient and privacy-preserving polygons spatial query framework for location-based services[J].IEEE Internet of Things Journal,2017,4(2):536-545. [3]He S,Chan S H G.WiFi fingerprint-based indoor positioning:Recent advances and comparisons[J].IEEE Communications Surveys & Tutorials,2016,18(1):466-490. [4]邓中亮,尹 露,唐诗浩,等.室内定位关键技术综述[J].导航定位与授时,2018,5(3):14-23. DENG Zhong-liang,YIN Lu,TANG Shi-hao,et al.A review of key technologies for indoor positioning[J].Navigation and Timing,2018,5(3):14-23. [5]Khalajmehrabadi A,Gatsis,Nikolaos,et al.Modern WLAN fingerprinting indoor positioning methods and deployment challenges[J].IEEE Communications Surveys & Tutorials,2017,19(3):1974-2002. [6]Sun J,Fu Y,He J,et al.Nonlinear programming-based ranging optimization for three-dimensional indoor time of arrival localization[J].International Journal ofDistributed Sensor Networks,2017,13(10):155014771773342. [7]Moreira A,Silva I,Meneses F,et al.Multiple simultaneous WiFi measurements in fingerprinting indoor positioning[C]//International Conference on Indoor Positioning & Indoor Navigation(IPIN),2017:1-8. [8]Dawes B,Chin K.A comparison of deterministic and probabilistic methods for indoor localization[J].The Journal of Systems and Software,2011,84:442-451. [9]Ge X,Qu Z.Optimization WIFI indoor positioning KNN algorithm location-based fingerprint[C]//IEEE International Conference on Software Engineering and Service Science(ICSESS),2016:135-137. [10]王博远,刘学林,蔚保国,等.WiFi指纹定位中改进的加权k近邻算法[J].西安电子科技大学学报,2019,46(5):41-47. WANG Bo-yuan,LIU Xue-lin,YU Bao-guo,et al.Improved weighted k-nearest neighbor algorithm for WiFi fingerprint positioning[J].Journal of Xidian University,2019,46(5):41-47. [11]朱宇佳,邓中亮,刘文龙,等.基于支持向量机多分类的室内定位系统[J].计算机科学,2012,39(4):32-35. ZHU Yu-jia,DENG Zhong-liang,LIU Wen-long,et al. Indoor positioning system based on support vector machine multi-classification[J].Computer Science,2012,39(4):32-35. [12]Wang X,Gao L,Mao S,et al.CSI-based fingerprinting for indoor localization:A deep learning approach[C]//IEEE Transactions on Vehicular Technology,2017:763-776. [13]Zhou R,Lu S,Chen J,et al.An optimized space partitioning technique to support two-layer WiFi fingerprinting[C]//Wireless Communications & Networking Conference.IEEE,2017:1-6. [14]桑 楠,袁兴中,周 瑞.基于SVM分类和回归的WiFi室内定位方法[J].计算机应用研究,2014,31(6):1820-1823. SANG Nan,YUAN Xing-zhong,ZHOU Rui.A WiFi indoor positioning method based on SVM classification and regression[J].Application Research of Computers,2014,31(6):1820-1823. [15]Jedari E,Wu Z,Rashidzadeh R,et al.WiFi based indoor location positioning employing random forest classifier[C]//2015 International Conference on Indoor Positioning and Indoor Navigation(IPIN),2015:1-5. [16]郭 妍,陈 晓,任晓晔.一种优化随机森林模型的室内定位方法[J].激光杂志,2018,39(10):70-74. GUO Yan,CHEN Xiao,REN Xiao-ye.An indoor positioning method for optimizing random forest models[J].Laser Journal,2018,39(10):70-74. [17]李 军,何星,蔡云泽,等.基于K-means和Random Forest的WiFi室内定位方法[J].控制工程,2017,24(4):787-792. LI Jun,HE Xing,CAI Yun-ze,et al.A WiFi indoor positioning method based on K-means and Random Forest[J].Control Engineering,2017,24(4):787-792. [18]Friedman J H.Stochastic gradient boosting[J].Computational Statistics & Data Analysis,2002 38(4):367-378. [19]Qiu X,Zuo Y,Liu G.ETCF:An ensemble model for CTR prediction[C]//IEEE International Conference on Service Systems and Service Management(ICSSSM),2018:1-5. [20]Ma X,Ding C,Luan S,et al.Prioritizing influential factors for freeway incident clearance time prediction using the gradient boosting decision trees method[J].IEEE Transactions on Intelligent Transportation Systems,2017,18(9):2303-2310. [21]Davidson P,Collin J,Takala J.Application of particle filters for indoor positioning using floor plans[C]//2010 Ubiquitous Positioning Indoor Navigation and Location Based Service.IEEE,2010:1-4. [22]王克会.基于WiFi和隐马尔可夫模型的室内定位算法研究[J].计算机时代,2018(1):9-12. WANG Ke-hui.Research on indoor positioning algorithm based on WiFi and hidden Markov model[J].Computer Era,2018(1):9-12. [23]Wang H,Deng Z,Fu X,et al.Ray-tracing aided indoor bayesian positioning algorithm[C]//China Satellite Navigation Conference.Springer,Singapore,2018:589-599.

备注/Memo

备注/Memo:
收稿日期:2019-12-29 责任编辑:高 佳
基金项目:国家自然科学基金(61801372)
通信作者:康晓非(1973-),男,陕西武功人,博士,副教授,E-mail:949592499@qq.com
更新日期/Last Update: 2020-05-15