[1]黄先龙,黄良璜,谢佳俊,等.一种基于PSO-BPNN的CSI指纹定位方法[J].江西师范大学学报(自然科学版),2023,(04):393-399.[doi:10.16357/j.cnki.issn1000-5862.2023.04.09]
　HUANG Xianlong,HUANG Lianghuang,XIE Jiajun,et al.The CSI Fingerprint Location Method Based on PSO-BPNN[J].Journal of Jiangxi Normal University:Natural Science Edition,2023,(04):393-399.[doi:10.16357/j.cnki.issn1000-5862.2023.04.09]
点击复制

一种基于PSO-BPNN的CSI指纹定位方法()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年04期
页码:
393-399
栏目:
信息科学与技术
出版日期:
2023-07-25

文章信息/Info

Title:
The CSI Fingerprint Location Method Based on PSO-BPNN
文章编号:
1000-5862(2023)04-0393-07
作者:
黄先龙1; 黄良璜1; 谢佳俊2; 余 敏1*
(1.江西师范大学计算机信息工程学院,江西 南昌 330022; 2.江西师范大学数字产业学院,江西 上饶 334000)
Author(s):
HUANG Xianlong1;  HUANG Lianghuang1;  XIE Jiajun2;  YU Min1*
(1.College of Computer Information Engineering, Jiangxi Normal University, Nanchang Jiangxi 330022, China; 2.College of Digital Industry, Jiangxi Normal University, Shangrao Jiangxi 334000, China)
关键词:
信道状态信息;  主动定位;  BP神经网络;  粒子群优化
Keywords:
channel status information;  active positioning;  BP neural network;  particle swarm optimization
分类号:
TN 92; TP 183
DOI:
10.16357/j.cnki.issn1000-5862.2023.04.09
文献标志码:
A
摘要:
针对传统定位方法定位精度低,BP神经网络易陷入局部最优的问题,该文提出了基于信道状态信息(channel state information,CSI)和粒子群算法优化BP神经网络(particle swarm optimization BP neural network,PSO-BPNN)的主动定位方法.该方法需要目标人员携带设备,利用CSI的幅值和相位共同作为指纹特征,采用3倍标准差法处理数据,达到去除异常值的效果,并利用粒子群优化算法初始化BP神经网络的权值和阈值,解决BP神经网络收敛速度差和容易陷入局部最小值的问题.实验结果表明:该文提出的PSO-BPNN定位方法平均定位误差为1.19 m,相比采用快速正交搜索算法和BP神经网络(FOS-BPNN)方法得到的定位误差降低了39.3%,相比采用CSI相位差矫正和BP神经网络(PD-BPNN)方法得到的定位误差降低了16.2%.
Abstract:
Aiming at the low positioning accuracy of traditional positioning methods and the problem that BP neural network is prone to fall into local optimization, the active positioning method based on channel state information(CSI)and particle swarm optimization BP neural network(PSO-BPNN)is proposed.This method requires people to carry the equipment,uses the amplitude and phase of CSI as the fingerprint feature, uses the three times standard deviation method to process the data, achieves the effect of removing outliers,and uses particle swarm optimization algorithm to initialize the weight and threshold of BP neural network,in order to solve the problem of poor convergence speed of BP neural network and easy to fall into local minimum.The experimental results show that the average positioning error of the proposed PSO-BPNN positioning method is 1.19m,which is 39.3% lower than that obtained by the method using Fast Orthogonal Search Algorithm and BP Neural Network(FOS-BPNN), and 16.2% lower than that obtained by using CSI phase difference correction and BP neural network(PD-BPNN).

参考文献/References:

[1] 陈锐志,陈亮.基于智能手机的室内定位技术的发展现状和挑战 [J].测绘学报,2017,46(10):1316-1326.
[2] 陈锐志,叶锋.基于Wi-Fi信道状态信息的室内定位技术现状综述 [J].武汉大学学报(信息科学版),2018,43(12):2064-2070.
[3] YU Min, YAO Shuyin, WU Xuan, et al. Research on a wi-fi RSSI calibration algorithm based on WOA-BPNN for indoor positioning [J].Applied Sciences,2022,12(14):7151.
[4] 刘芬. 基于信道状态信息的室内定位算法研究 [D].徐州:中国矿业大学,2021.
[5] LI Jinsong,LI Yunzhou, JI Xinsheng.A novel method of Wi-Fi indoor localization based on channel state information [EB/OL].[2022-02-06]. https://ieeexplore.ieee.org/document/7752710.
[6] 党小超,任家驹,郝占军.基于CSI相位差值矫正的室内定位算法 [J].计算机工程,2019,45(2):18-25.
[7] PIRZADA N, NAYAN M Y, SUBHAN F, et al. Comparative analysis of active and passive indoor localization systems [J]. AASRI Procedia, 2013, 5(3):92-97.
[8] HALPERIN D,HU Wenjun, SHETH A, et al. Predictable 802.11 packet delivery from wireless channel measurements [J]. Acm Sigcomm Computer Communication Review, 2010, 40(4):159-170.
[9] CHIZHIK D,LING Jonathan,WOLNIANSKY P W, et al. Multiple-input-multiple-output measurements and mode-ling in Manhattan [J]. IEEE Journal on Selected Areas in Communications,2006,21(3):321-331.
[10] WANG Xuyu, GAO Lingjun, MAO Shiwen,et al. DeepFi: Deep learning for indoor fingerprinting using channel state information[EB/OL].[2022-01-19]. https://ieeexplore.ieee.org/document/7127718.
[11] LIU Dong, LIU Zhigang, SONG Zhixin. LDA-based CSI amplitude fingerprinting for device-free localization[EB/OL].[2022-01-23]. https://ieeexplore.ieee.org/abstract/document/9164348.
[12] 周明快,黄巍,陈滨,等.基于无线信道状态相位信息优化的定位算法 [J].传感技术学报,2018,31(6):957-962.
[13] WANG Xuyu, GAO Lingjun, MAO Shiwen. CSI phase fingerprinting for indoor localization with a deep learning approach [J].IEEE Internet of Things Journal,2016,3(6):1113-1123.
[14] 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.
[15] 李辉,蔡敏,李宇,等.基于自适应粒子群优化算法的神经网络的优化研究 [J].江西师范大学学报(自然科学版),2010,34(6):632-635.

备注/Memo

备注/Memo:
收稿日期:2022-12-25
基金项目:中央引导地方科技发展资金——跨区域研发合作课题(20222ZDH04090)资助项目.
通信作者:余 敏(1964—),女,江西南昌人,教授,博士生导师,主要从事无线传感器网络与技术等研究.E-mail:myu@jxnu.edu.cn
更新日期/Last Update: 2023-07-25