众包室内定位系统中基于多维尺度变换的接收信号强度平滑理论  

Received Signal Strength Smoothing Method Based on Multidimensional Scaling for Crowdsourcing Indoor Positioning

作　　者：张立晔 王壮 房超 孟晓亮 田爱奎[1] ZHANG Li-ye;WANG Zhuang;FANG Chao;MENG Xiao-liang;TIAN Ai-kui(School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China)

机构地区：[1]山东理工大学计算机科学与技术学院,淄博255000

出　　处：《科学技术与工程》2021年第33期14181-14187,共7页Science Technology and Engineering

基　　金：国家自然科学基金(62001272);山东省自然科学基金(ZR2019BF022)。

摘　　要：基于无线局域网(wireless local area network,WLAN)指纹的定位方法具有成本低、可用性好等优点,近年来越来越受到人们的关注。为了实现室内定位系统的快速部署,通常采用众包技术替代传统部署方法。在离线阶段建立radio map数据库时,由于利用众包技术采集的接收信号强度(received signal strength,RSS)数据量大大减少,使得RSS数据中的噪声和采集误差无法得到有效抑制,造成建立的radio map精度较低,定位误差增大。针对该问题,提出了一种基于多维尺度变换(multidimensional scaling,MDS)算法的RSS平滑理论。利用相邻位置RSS数据之间的相关性,在每个位置推断出一个最优RSS值,从而实现抑制噪声和消除采集误差的作用,最终得到更平滑的radio map,提高定位精度。实验结果表明,采用MDS方法达到了预期的目标。Fingerprint location method based on wireless local area network(WLAN)has the advantages of low cost and good availability.In recent years,it has attracted more and more attention.In order to rapidly deploy the indoor positioning system,the crowdsourcing method was applied to alternate the traditional deployment method.When building a radio map,much fewer RSS values were needed using the crowdsourcing method compared to conventional methods,which lends greater influence to noises and erroneous measurements in RSS values.A multidimensional scaling(MDS)based received signal strength(RSS)smoothing method was proposed to solve the serious problem in crowdsourcing indoor positioning system.Accordingly,an imprecise radio map was built based on these imprecise RSS values.In order to acquire a smoother radio map and improve the localization accuracy,the MDS method was used to infer an optimal RSS value at each location by exploiting the correlation of RSS values at nearby locations.Experimental results show that the expected goal is achieved by the proposed method.

关 键 词：室内定位系统 众包技术 多维尺度变换 RSS平滑理论 

分 类 号：TN919[电子电信—通信与信息系统]