Multi-source information fusion indoor positioning method based on genetic algorithm to optimize neural network

被引：0
|
作者：
Liu Y. [1 ]
Hui H. [1 ]
Lu Y. [1 ]
Zou X. [1 ]
Yang Y. [2 ]
Cao J. [1 ]
机构：
[1] Chongqing engineering research center of intelligent sensing technology and microsystem, Chongqing University of Post and Telecommunications, Chongqing
[2] Guizhou Aerospace Control Technology Co., Ltd., 550009, Guizhou
来源：
Zhongguo Guanxing Jishu Xuebao/Journal of Chinese Inertial Technology | 2020年 / 28卷 / 01期
关键词：
BP neural network; Genetic algorithm; Indoor positioning; Multi-source information fusion;
D O I：
10.13695/j.cnki.12-1222/o3.2020.01.011
中图分类号：
学科分类号：
摘要：
In order to reduce the error of single source positioning technology in complex indoor environment, a multi-source information fusion indoor positioning method based on genetic algorithm to optimize neural network is proposed. Firstly, the matching range of geomagnetism is constrained by WiFi positioning method to reduce mismatch rate. Then genetic algorithm is used to find the global optimal solution of the network to optimize the initial weight and threshold of the BP neural network, and improve the network accuracy and convergence speed. The optimized network is used to train and fuse the combined positioning result and the Pedestrian Dead Reckoning positioning result in the true position coordinate direction to obtain the optimal positioning result. According to the experiment data, the mean square error of BP neural network is reduced by about 75% after optimized by genetic algorithm, and the accuracy of fusion positioning is improved by about 47% on average. The proposed method can effectively improve the positioning accuracy and has better positioning performance. © 2020, Editorial Department of Journal of Chinese Inertial Technology. All right reserved.
引用
下载
收藏
页码：67 / 73
页数：6
相关论文
共 10 条
  • [1] Chen Y., Lymberopoulos D., Liu J., Et al., Indoor localization using FM signals, IEEE Transactions on Mobile Computing, 12, 8, pp. 1502-1517, (2013)
  • [2] Rai A., Chintalapudi K.K., Padmanabhan V.N., Et al., Zee: zero-effort crowdsourcing for indoor localization, (2012)
  • [3] Belakbir A., Amghar M., Sbiti N., Et al., An indoor-outdoor positioning system based on the combination of GPS and UWB sensors, Journal of Theoretical & Applied Information Technology, 25, 3-4, pp. 301-303, (2014)
  • [4] Li Y., Zhuang, Y, Zhang, P, Et al., An improved inertial/wifi/magnetic fusion structure for indoor navigation, Information Fusion, 34, C, pp. 101-119, (2017)
  • [5] Xin L., Wang J., Liu C., A bluetooth/PDR integration algorithm for an indoor positioning system, Sensors, 15, 10, pp. 24862-24885, (2015)
  • [6] Li N., Chen J., Yuan Y., Combined pedestrian localization algorithm based on WiFi/PDR, Journal of Chinese Inertial Technology, 25, 4, pp. 483-487, (2017)
  • [7] Xia L., Geng J., Xiao J., Et al., Ellipsoid fitting based two-step optimized correction for orthogonal tri-axis magnetic compass measurements, Journal of Chinese Inertial Technology, 26, 4, pp. 478-483, (2018)
  • [8] Hang C., Rui Z., Chen Z., Et al., Dynamic gesture recognition method based on improved DTW algorithm, International Conference on Industrial Informatics-computing Technology, (2017)
  • [9] Li C., Zong X., Gudake, A survey of online fault diagnosis for PV module based on BP neural network, International Conference on Smart City & Systems Engineering, (2017)
  • [10] Hoseinian F., Abdollahzadeh A., Rezai B., Power prediction of semi-self-grinding machine based on hybrid neural genetic algorithm, Journal of Central South University, 25, 1, pp. 151-158, (2018)
1