基于WiFi-BP的室内定位算法

doi:10.16180/j.cnki.issn1007-7820.2020.08.013

摘要/Abstract

摘要：

针对设备差异性造成信号偏差从而影响定位精度的问题,提出了一种结合BP神经网络和加权质心定位算法的室内定位算法。文中通过离群点检测算法对不同手机的RSSI数据进行清洗,并以清洗后的数据作为BP神经网络的数据源进行模型训练,得到了一种稳定的非线性的BP模型。在此基础上,结合改进的室内定位算法进行室内定位。实验结果表明,文中所提定位算法的均值误差、最小误差和最大误差分别为为0.58 m、0.24 m和1.06 m,定位精度明显高于现有的同类算法。

关键词: 设备差异性, 接收信号强度指示, 室内定位, BP神经网络, 离群点检测, 加权质心定位

Abstract:

Aiming at the problem that signal deviation caused by the device variability affects positioning accuracy, an indoor positioning algorithm combining BP neural network and weighted centroid positioning algorithm was proposed. In this paper, the RSSI data of different mobile phones were cleaned by outlier detection algorithm, and the cleaned data was used as the data source of BP neural network to train the model, thus obtaining a stable nonlinear BP model. On this basis, combined with the improved indoor positioning algorithm for indoor positioning. Experiment results showed the mean error, minimum error and maximum error of the proposed algorithm were 0.58 m, 0.24 m and 1.06 m, respectively, and the positioning accuracy was significantly higher than that of the existing similar algorithms.

Key words: the device variability, received signal strength indication, indoorpositioning, BP neural network, the outlier detection, weighted centroid positioning

中图分类号:

TN92

朱轶峰. 基于WiFi-BP的室内定位算法[J]. 电子科技, 2020, 33(8): 74-79.

ZHU Yifeng. Indoor Positioning Algorithm Based on WiFi-BP[J]. Electronic Science and Technology, 2020, 33(8): 74-79.

图/表 11

图1

图2

图3

图4

图5

图6

图7

表1

表2

图8

图9

参考文献 16

[1]	靳超, 邱冬炜. 基于WiFi信号室内定位技术的研究[J]. 测绘通报, 2017(5):21-25.
	Jin Chao, Qiu Dongwei. Research on indoor localization technology based on WiFi signal[J]. Bulletin of Surveying and Mapping, 2017(5):21-25.
[2]	王琦. 基于RSSI测距的室内定位技术[J]. 电子科技, 2012,25(6):64-66.
	Wang Qi. Research on an indoor positioning technology based on RSSI ranging[J]. Electronic Science and Technology, 2012,25(6):64-66.
[3]	项亚南, 潘丰. 一种基于无线传感器网络的加权阈值质心定位算法[J]. 传感器与微系统, 2014,33(9):104-106.
	Xiang Yanan, Pan Feng. A weighted threshold centroid localization algorithm based on WSNs[J]. Transducer and Microsystem Technologies, 2014,33(9):104-106.
[4]	王亚民, 王海英, 何佩伦. 基于RSSI的改进加权质心定位算法[J]. 计算机工程与设计, 2016,37(11):2865-2868.
	Wang Yamin, Wang Haiying, He Peilun. Improved weighted centroid localization algorithm based on RSSI[J]. Computer Engineering and Design, 2016,37(11):2865-2868.
[5]	贾银山, 曾帅斌, 王璟. 一种基于优化RSSI精度的加权质心定位算法[J]. 计算机应用与软件, 2017,34(11):162-165.
	Jia Yinshan, Zeng Shuaibin, Wang Jing. A weighted centroid localization algorithm based on optimized RSSI precision[J]. Computer Applications and Software, 2017,34(11):162-165.
[6]	路泽忠, 卢小平, 付睢宁, 等. 一种改进的RSSI加权质心定位算法[J]. 测绘科学, 2019,44(1):26-31.
	Lu Zezhong, Lu Xiaoping, Fu Suining, et al. An improved weighted centroid indoor positioning based on RSSI[J]. Science of Survery and Mapping, 2019,44(1):26-31.
[7]	刘晓晨, 张静. 基于改进BP神经网络的室内无线定位方法[J]. 计算机应用与软件, 2016,33(6):114-117.
	Liu Xiaochen, Zhang Jing. Indoor wireless positioning based on improved BP network[J]. Computer Applications and Software, 2016,33(6):114-117.
[8]	Li Q, Li W, Sun W, et al. Fingerprint and assistant nodes based WiFi localization in complex indoor environment[J]. IEEE Access, 2017(4):2993-3004.
[9]	Meng H, Yuan F, Yan T, et al. Indoor positioning of RBF neural network based on improved fast clustering algorithm combined with LM algorithm[J]. IEEE Access, 2019(7):5932-5945.
[10]	宋斌斌, 余敏, 何肖娜, 等. 一种BP神经网络的室内定位WiFi标定方法[J]. 导航定位学报, 2019,7(1):43-47.
	Song Binbin, Yu Min, He Xiaona, et al. An indoor location WiFi calibration method based on BP neural network[J]. Journal of Navigation and Positioning, 2019,7(1):43-47.
[11]	曹雪朋, 施伟斌. 基于RSSI的WSN室内定位系统研究[J]. 电子科技, 2017,30(1):94-96.
	Cao Xuepeng, Shi Weibin. Study of WSN indoor postioning system based on RSSI[J]. Electronic Science and Technology, 2017,30(1):94-96.
[12]	刘运杰, 金明录, 崔承毅. 基于RSSI的无线传感器网络修正加权质心定位算法[J]. 传感技术学报, 2010,23(5):717-721.
	Liu Yunjie, Jin Minglu, Cui Chengyi. Modified weighted centroid localization algirithm based on RSSI for WSN[J]. Chinese Journal of Sensors and Actuators, 2010,23(5):717-721.
[13]	叶冬芬, 杨明霞, 范伟, 等. 无线传感网离群点检测技术研究综述[J]. 计算机应用研究, 2015,32(7):1937-1941.
	Ye Dongfen, Yang Mingxia, Fan Wei, et al. Outlier detection techniques for wireless sensor networks: a survery[J]. Application Research of Computers, 2015,32(7):1937-1941.
[14]	程杰. 基于欧式距离平均值的离群点自动检测算法[J]. 电脑知识与技术, 2015,11(7):240-242.
	Cheng Jie. Automatic outlier detection algorithm based on euclidean distance average[J]. Computer Knowledge and Technology, 2015,11(7):240-242.
[15]	Wang C, Wu F, Shi Z, et al. Indoor positioning technique by combining RFID and particle swarm optimization-based back propagation neural network[J]. Optik, 2016,127(17):6839-6849. doi: 10.1016/j.ijleo.2016.04.123
[16]	施伟, 高军. 无线传感器网络中基于RSSI的改进加权质心定位算法[J]. 计算机应用与软件, 2015,32(12):68-70.
	Shi Wei, Gao Jun. An improved weighted centroid localisation algorithm based on RSSI for wireless sensor networks[J]. Computer Applications and Software, 2015,32(12):68-70.

序号	实测坐标	加权质心定位算法	改进加权质心定位算法	本文算法
P₁	(2.69,9.32)	(1.65,11.20)	(3.12,8.07)	(3.11,8.58)
P₂	(5.14,9.14)	(5.42,10.40)	(5.69,10.52)	(5.38,10.17)
P₃	(5.18,46.75)	(6.13,6.86)	(5.83,6.96)	(5.59,6.36)
P₄	(2.92,3.76)	(2.31,4.35)	(2.38,5.65)	(2.51,4.89)
P₅	(4.90,4.64)	(5.34,4.28)	(5.18,4.24)	(5.25,4.68)
P₆	(7.39,5.96)	(7.79,5.82)	(7.08,5.72)	(7.27,5.75)

序号	加权质心算法真误差/m	改进加权质心算法真误差/m	本文算法真误差/m
P₁	1.17	0.62	0.41
P₂	0.81	0.86	0.75
P₃	0.82	0.72	0.58
P₄	0.56	0.37	0.32
P₅	0.39	0.27	0.24
P₆	0.29	0.24	0.20