K近邻快速匹配的WiFi指纹定位方法  

Fast matching method of K nearest neighbor for WiFi fingerprint localization

作　　者：罗宇锋[1] 刘艳辉 王国东 LUO Yu-feng;LIU Yan-hui;WANG Guo-dong(School of Electrical Engineering ＆ Automation,Henan Polytechnic University,Jiaozuo 454003,China;Wuxi Jiuyu Architectural Design Institute Co Ltd,Wuxi 214000,China)

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454003 [2]无锡九宇建筑设计院有限公司,江苏无锡214000

出　　处：《传感器与微系统》2018年第8期22-24,28,共4页Transducer and Microsystem Technologies

基　　金：河南理工大学博士基金资助项目(72515/168)

摘　　要：为解决室内Wi Fi指纹定位速度慢及定位波动大的问题,采用高斯拟合和多次测量取平均值的方法对接收的信号进行平滑处理;以距离为相似性测度,规定一个阈值对建立指纹数据库进行分类;改进K近邻算法,并在分类的基础上实现K近邻快速匹配。实验结果表明:经过分类处理过的定位系统耗时有很大程度的改善,平均降幅62.8%;Wi Fi指纹定位精度的平均误差从4.17 m降到了2.12 m。Aiming at the problem of low localization speed and big positioning fluctuations of indoor WiFi fingerprints positioning,use the method of Gauss l＇itting and averaging by muhimetering and smoothing proeessing on received signal. Use distance as similarity measurement, set a threshold to classiC＇ fingerprint database. By improving K nearest neighbor algorithm and on the basis of classific.ation,implement fast matching of＇ K nearest neighbor. The experimental resuhs show that the time efficiency of the classified localization system is greatly improved,with an average decreasing anplitude of 62.8 % ;average error of WiFi fingerprint positioning decrease from 4.17 m to 2.12 m.

关 键 词：高斯拟合 多次测量取平均值 数据库分类 K近邻快速匹配 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]