一种基于堆叠自编码器的WiFi室内定位算法  

Stacked denoising autoencoders WiFi-based indoor localization algorithm

作　　者：马佩勋[1] MA Peixun(Software Institute,Changsha Social Work College,Changsha 410004,China)

机构地区：[1]长沙民政职业技术学院软件学院,长沙410004

出　　处：《导航定位学报》2021年第3期55-59,85,共6页Journal of Navigation and Positioning

基　　金：2019年度中国残联研究课题项目(CJFJRRB04-2019)。

摘　　要：由于室内无线保真(WiFi)可随处接入,基于WiFi指纹的室内定位算法得到广泛关注。然而,由于噪声和无线信号的不稳定性,基于WiFi指纹的室内定位算法的定位精度并不高。为此,提出基于堆叠自编码器的WiFi室内定位(SDIL)算法。SDIL算法结合堆叠去噪声自编码深度学习模型和贝叶斯推断处理WiFi信号内的噪声,并捕获WiFi接入点信号与其位置间的复杂关系。实验结果表明,SDIL算法能够在室内达到米级的平均定位精度。Due to the ubiquitous availability of Wireless Fidelity(WiFi)indoors,many indoor localization systems have been proposed relying on WiFi fingerprinting.However,due to the inherent noise and instability of the wireless signals,the localization accuracy usually degrades.Therefore,Stacked Denoising Autoencoders WiFi-based Indoor Localization(SDIL)algorithm is proposed in this paper.SDIL algorithm combines a stacked denoising autoencoders deep learning model and a probabilistic framework to handle the noise in the received WiFi signal and capture the complex relationship between the WiFi Access Points(APs)signals heard by the mobile phone and its location.The results show that it can achieve a mean localization accuracy of meter level.

关 键 词：室内定位 无线保真 深度学习 堆叠去噪声自编码 贝叶斯推断 

分 类 号：P228[天文地球—大地测量学与测量工程]