基于XGBoost预测及弹性网误差补偿的室内定位算法

doi:10.16182/j.issn1004731x.joss.20-0866

摘要/Abstract

摘要：

为解决室内定位系统中因环境动态变化而导致定位精度下降的问题，提出一种基于XGBoost并融合弹性网的误差补偿算法。采用XGBoost定位模型对目标位置进行初步预测，当室内环境改变后，再采用弹性网算法构建误差补偿模型，修正XGBoost定位模型的定位误差，并与基于K近邻、支持向量机、随机森林、梯度提升决策树等定位算法做对比。实验结果表明：在更新15%指纹数据库样本的情况下，该算法在80%分位处的定位精度控制在0.73 m以内，明显优于其他定位算法，且较基于XGBoost的定位算法精度提高了25.5%。

关键词: 室内定位, WiFi指纹, 极限梯度提升, 弹性网, 误差补偿

Abstract:

Arming at the decreased positioning accuracy caused by the environment dynamic change of indoor positioning system, an error compensation algorithm based on XGBoost fusion elastic net is proposed. XGBoost positioning model is used to make a preliminary prediction on the target position. When the indoor environment changes, the elastic net algorithm is used to construct an error compensation model to correct the positioning error of XGBoost positioning model. The experimental results show that when only 15% of the fingerprint database samples need to be updated, the positioning accuracy of the proposed algorithm is controlled in 0.73m at the 80% percentile, which is significantly better than those of the K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF) and gradient boosting decision tree (GBDT) positioning algorithms, and the accuracy increases 25.5% than XGBoost.

Key words: indoor positioning, WiFi fingerprint, XGBoost, elastic net, error compensation

中图分类号:

TP391

康晓非, 曾璇, 乔威. 基于XGBoost预测及弹性网误差补偿的室内定位算法[J]. 系统仿真学报, 2022, 34(4): 719-726.

Xiaofei Kang, Xuan Zeng, Wei Qiao. Indoor Positioning Algorithm Based on XGBoost Prediction and Elastic Net Error Compensation[J]. Journal of System Simulation, 2022, 34(4): 719-726.

图/表 7

图1

图2

图3

图4

表1

图5

图6

参考文献 26

1	Zafari F, Gkelias A, Leung K K. A Survey of Indoor Localization Systems and Technologies[J]. IEEE Communications Surveys & Tutorials (S1553-877X), 2019, 21(3): 2568-2599.
2	Li Z, Xu K, Wang H, et al. Machine-Learning-Based Positioning: A Survey and Future Directions[J]. IEEE Network (S0890-8044), 2019, 33(3): 96-101.
3	Peneda L, Azenha A, Carvalho A. Trilateration for Indoors Positioning within the Framework of Wireless Communications[C]//2009 35th Annual Conference of IEEE Industrial Electronics. Porto, Portugal: IEEE, 2009: 2732-2737.
4	Peterson B B, Kmiecik C, Hartnett R, et al. Spread Spectrum Indoor Geolocation[J]. Navigation (S2161-4296), 1998, 45(2): 97-102.
5	Yamasaki R, Ogino A, Tamaki T, et al. TDOA Location System for IEEE 802.11 b WLAN [C]//IEEE Wireless Communications and Networking Conference. New Orleans, LA, USA: IEEE, 2005: 2338-2343.
6	Kim H. Double-sided Two-Way Ranging Algorithm to Reduce Ranging Time[J]. IEEE Communications Letters(S1558-2558), 2009, 13(7): 486-488.
7	Van Veen B D, Buckley K M. Beamforming: A Versatile Approach to Spatial Filtering[J]. IEEE Assp Magazine (S0740-7467), 1988, 5(2): 4-24.
8	Sadeghi H, Valaee S, Ocrapose Shirani S.. An Indoor Positioning System Using Smartphone/Tablet Cameras and OCR-aided Stereo Feature Matching[C]//2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). South Brisbane, Queensland, Australia: IEEE, 2015: 1473-1477.
9	Vedadi F, Valaee S. Automatic Visual Fingerprinting for Indoor Image-Based Localization Applications[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems (S2168-2216), 2017, 50(1): 305-317.
10	Davidson P, Piché R. A Survey of Selected Indoor Positioning Methods for Smartphones[J]. IEEE Communications Surveys & Tutorials (S1553-877X), 2016, 19(2): 1347-1370.
11	Sorour S, Lostanlen Y, Valaee S, et al. Joint Indoor Localization and Radio Map Construction with Limited Deployment Load[J]. IEEE Transactions on Mobile Computing (S1536-1233), 2014, 14(5): 1031-1043.
12	Ge X, Qu Z. Optimization WIFI Indoor Positioning KNN Algorithm Location-Based Fingerprint[C]//2016 7th IEEE International Conference on Software Engineering and Service Science. Beijing, China: IEEE, 2016: 135-137.
13	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 Xingzhong, Zhou Rui. A WiFi Indoor Positioning Method Based on SVM Classification and Regression[J]. Application Research of Computers,2014,31(6): 1820-1823.
14	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 Xiaoye. An Indoor Positioning Method for Optimizing Random Forest Models[J]. Laser Journal, 2018, 39(10): 70-74.
15	Sou S I, Lin W H, Lan K C, et al. Indoor Location Learning over Wireless Fingerprinting System with Particle Markov Chain Model[J]. IEEE Access (S2169-3536), 2019, 7(4): 8713-8725.
16	Li M, Kang X, Qiao W. Performance Comparison and Evaluation of Indoor Positioning Technology Based on Machine Learning Algorithms[C]//2019 IEEE 19th International Conference on Communication Technology (ICCT). Xi'an, China: IEEE, 2019: 456-460.
17	Wang J, Park J G. A Novel Fingerprint Localization Algorithm Based on Modified Channel State Information Using Kalman Filter[J]. Journal of Electrical Engineering & Technology (S1975-0102), 2020, 15(6): 1811-1819.
18	Lipka M, Sippel E, Vossiek M. An Extended Kalman Filter for Direct, Real-Time, Phase-Based High Precision Indoor Localization[J]. IEEE Access (S2169-3536), 2019, 7(3): 25288-25297.
19	Gu F, Hu X, Ramezani M, et al. Indoor Localization Improved by Spatial Context-a Survey[J]. ACM Computing Surveys (CSUR) (S0360-0300), 2019, 52(3): 1-35.
20	Villacrés J L C, Zhao Z, Braun T, et al. A Particle Filter-Based Reinforcement Learning Approach for Reliable Wireless Indoor Positioning[J]. IEEE Journal on Selected Areas in Communications (S0733-8716), 2019, 37(11): 2457-2473.
21	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, 40(3): 470-476.
	Kang Xiaofei, Li Mengmeng, Qiao Wei. High-precision Indoor Localization Fusion Algorithm Based on WiFi Fingerprint[J]. Journal of Xi'an University of Science and Technology, 2020, 40(3): 470-476.
22	Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System[C]//22nd ACM Sigkdd International Conference on Knowledge Discovery and data mining. San Francisco, United States: Association for Computing Machinery, 2016: 785-794.
23	张玄黎, 修春娣, 王延昭, 等. 基于CSI-XGBoost的高精度WiFi室内定位算法[J]. 北京航空航天大学学报, 2018, 44(12):77-85.
	Zhang Xuanli, Xiu Chundi, Wang Yanzhao, et al. High-precision WiFi Indoor Localization Algorithm Based on CSI-XGBoost [J]. Journal of Beijing University of Aeronautics and Astronsutics, 2018, 44(12): 77-85.
24	Zou H, Hastie T. Regularization and Variable Selection Via the Elastic Net[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodology) (S1467-9868), 2005, 67(2): 301-320.
25	李方敏, 张韬, 刘凯, 等. 基于距离测量和位置指纹的室内定位方法研究[J]. 计算机学报, 2019, 42(2): 109-120.
	Li Fangmin, Zhang Tao, Liu Kai, et al. An Indoor Localization Method Based on Location Fingerprint and Range Measurement[J]. Chinese Journal of Computers, 2019, 42(2): 109-120.
26	Sinha R S, Hwang S H. Comparison of CNN Applications for RSSI-based Fingerprint Indoor Localization[J]. Electronics(S2079-9292), 2019, 8(9): 989-1113.

算法	平均定位精度/m	80%分位点精度/m	时间复杂度
KNN	2.02	2.75	O (n·m)
SVM	1.21	1.33	O (n²·m)
RF	1.02	1.48	O (n·log n·m·k)
GBDT	0.87	1.01	O (n·log n·m·d)
XGBoost	0.71	0.98	O (p·log n+k·d·p)
XGBoost-EC	0.47	0.73	O (p·log n+k·d·p)

[1]	唐红, 王栋, 宋博, 褚文奎, 何林远. 基于非线性赋权XGBoost算法的航班延误分类预测[J]. 系统仿真学报, 2021, 33(9): 2261-2269.
[2]	于广宇, 董学平, 王祥民, 甘敏. 弹性网下基于LSTM的分解炉出口温度预测[J]. 系统仿真学报, 2021, 33(5): 1078-1085.
[3]	朱政泽, 周海鹰, 付勇智, 周奎, 王思山, 龚家元, 邓思豪, 侯昆明. 基于延迟补偿的网联式自主驾驶车辆协同控制[J]. 系统仿真学报, 2019, 31(7): 1448-1459.
[4]	胡东方, 郭建伟. 弧面凸轮的非等径廓面加工误差控制[J]. 系统仿真学报, 2019, 31(4): 727-732.
[5]	孔红山, 郁滨. 一种基于BP神经网络的VIRE改进算法研究[J]. 系统仿真学报, 2018, 30(9): 3586-3595.
[6]	常帅兵, 谭文, 曾智勇. 具有调速器死区的LFC系统的广义自抗扰控制[J]. 系统仿真学报, 2017, 29(4): 818-825.
[7]	李军, 陈颖. KPCA-ESN方法在Wi-Fi室内定位中的应用[J]. 系统仿真学报, 2017, 29(12): 3042-3050.
[8]	王乐, 罗宇, 王海宽, 费敏锐. ToF深度相机测量误差校正模型[J]. 系统仿真学报, 2017, 29(10): 2323-2329.