王军选;王漪楠;

• 1:西安邮电大学通信与信息工程学院

摘要(Abstract)：

为了有效地降低室内多变的传播环境带来的多径效应和非视距(non-line of sight,NLOS)的传播误差,提出一种在第五代移动通信技术(5th generation mobile communication technology,5G)室内小小区场景下,结合深度神经网络(deep neural network,DNN)和多天线的多信号分类算法(multiple signal classification,MUSIC)的联合室内定位方案。首先, MUSIC利用用户终端上传的通信系统数据估计到达角度(angle of arrival,AOA)。其次,将接收信号强度指示(radio signal strength indication,RSSI)数据输入离线阶段训练好的DNN模型中,估计用户终端的直线距离。最后,利用DNN和AOA算法将估计的信息输入联合定位系统中得到用户的二维坐标。仿真结果表明,该算法相比于路径损耗模型具有更小的定位误差,能够提升定位性能。

关键词(KeyWords)： 室内定位;第五代移动通信技术;深度神经网络;多信号分类

Abstract:

Keywords:

基金项目(Foundation): 国家重大专项项目(ZX201703001012-005)

作者(Author): 王军选;王漪楠;

Email:

DOI: 10.13682/j.issn.2095-6533.2020.04.007

参考文献(References)：

• [1] CLAUSSEN H ,HO L T W ,SAMUEL L G .Self-optimization of coverage for femtocell deployments[J].Wireless Telecommunications SymposiumWts,2008:278-285.DOI:10.1109/WTS.2008.4547576.
• [2] XIE Z,SRN B,TIAN Y.PSO-based spectrum sensing technology in femtocell networks[J].Systems Engineering and Electronics,2014,36(3):575-579.
• [3] GENG Y,HE J,PAHLAVAN K.Modeling the effect of human body on TOA based indoor human tracking[J].International Journal of Wireless Information Networks,2013,20(4):306-317.DOI:10.1007/s10776-013-0227-3.
• [4] BLANDIN C,OZEROV A,VINCENT E.Multi-source TDOA estimation in reverberant audio using angular spectra and clustering[J].Signal Processing,2012,92(8):1950-1960.DOI:10.1016/j.sigpro.2011.09.032.
• [5] ZHANG J,ZHANG L.Research on distance measurement based on RSSI of zigBee[C]// Proceedings of the 2009 ISECS International Colloquium on Computing,Communication,Control,and Management.[S.l.]:IEEE,2009:210-212.DOI:10.1109/CCCM.2009.5267883.
• [6] GARCIA N,WYMEERSCH H,SLOCK D.Optimal precoders for tracking the AoD and AoA of a mm-wave path[J].IEEE Transactions on Signal Processing,2018,66:5718-5729.DOI:10.1109/TSP.2018.2870368.
• [7] TIAN X,SHEN R,LIU D,et al.Performance analysis of RSS fingerprinting based indoor localization[J].IEEE Transactions on Mobile Computing,2017,16(10):2847-2861.DOI:10.1109/TMC.2016.2645221.
• [8] ZHANG Y J,LI S N.Indoor location based on an landmarc improved algorithm[J].Applied Mechanics & Materials,2014,687-691:4105-4109.DOI:10.4028/www.scientific.net/AMM.687-691.4105.
• [9] MERCURI M,PING J S,PANDEY G,et al.Analysis of an indoor biomedical radar-based system for health monitoring[J].IEEE Transactions on Microwave Theory&Techniques,2013,61(5):2061-2068.DOI:10.1109/TMTT.2013.2247619.
• [10] CHENG C Y.Indoor localization algorithm using clustering on signal and coordination pattern[J].Annals of Operations Research,2014,216(1):83-99.DOI:10.1007/s10479-012-1219-x.
• [11] WANG J,WEI W,WANG W,et al.RFID hybrid positioning method of phased array antenna based on neural network[J].IEEE Access,2018,6:74953-74960.DOI:10.1109/ACCESS.2018.2877396.
• [12] STHAPIT P,GANG H,PYUN J.Bluetooth based indoor positioning using machine learning algorithms[C]//Proceedings of the 2018 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia).Jeju:IEEE,2018:206-212.
• [13] LU H,XING L G,SHUANG L,et al.Indoor positioning technology based on deep neural networks[C]//Proceedings of the 2018 Ubiquitous Positioning,Indoor Navigation and Location-Based Services (UPINLBS).Wuhan:IEEE,2018:1-6.
• [14] YANG L,LIU Q,XU J,et al.An indoor RFID location algorithm based on support vector regression and particle swarm optimization[C]//Proceedings of the 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).Chicago:IEEE,2018:1-6.
• [15] XU H,WU M,LI P ,et al.An RFID indoor positioning algorithm based on support vector regression[J].MDPI,2018(5):1504-1519.DOI:10.3390/s18051504.
• [16] 毛永毅,谢川.基于遗传算法优化神经网络的定位算法[J].西安邮电大学学报,2014,19(4):45-48.DOI:10.13682/j.issn.2095-6533.2014.04.009.