基于变分自编码器的WLAN定位方法  

Variational auto encoder based WLAN positioning

作　　者：米伟娟[1] 李娜[1] Mi Weijuan;Li Na(Information Technology and Cultural Management Institue,Hebei Institute of Communication,Shijjazhuang 051430,China)

机构地区：[1]河北传媒学院信息技术与文化管理学院,石家庄051430

出　　处：《电子测量与仪器学报》2020年第12期101-108,共8页Journal of Electronic Measurement and Instrumentation

摘　　要：基于无线局域网络(WLAN)的定位是当前室内定位领域的主流技术之一。提出一种基于变分自编码器的WLAN定位方法,具备定位通路和接受信号强度(RSS)信号指纹重构通路,使得该方法既具备定位能力,也具备重新生成RSS信号指纹或指纹地图的能力。利用开源的数据集进行验证,证明了该方法在定位通路上,相比稀疏重构定位方法和传统k最邻近(kNN)定位方法,误差分别下降了约14%和24%;能够对指纹地图(RM)进行重新生成,利用重构的RM进行定位,相比于利用稀疏重构生成的RM定位误差下降了约11%。Wireless local area network(WLAN)based positioningis one of the main stream techniques for indoor positioning.In this paper,a WLAN based method is proposed based on a variational auto encoder(VAE),which contains a positioning path and a reconstruction path.This structure has enabled the ability to position along with reconstruction of RSS radio map(RM).The proposed methodis validated by open-sourced dataset,which shows that the proposed method can increase the positioning accuracy by about 14%and 24%respectively compared to the compressive sensing(CS)based methodand the traditional kNN method in the positioning path.Moreover,from the reconstructed RM,the method can have accuracy enhancement of about 11%in positioning than that from the CS reconstructed RM.

关 键 词：变分自编码器 WLAN定位 神经网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN96[自动化与计算机技术—计算机科学与技术]