摘 要:在指纹定位加权K 近邻算法中,传统欧氏距离度量原理简单,但会忽略掉样本单元不同特性之间存在的差别,导致定位误差较大。为了克服欧氏距离存在的不足,分别采用马氏距离、卡方距离将其替换,并结合加权K 近邻算法进行定位精度对比。试验结果表明,取相同K 值的情况下,基于马氏距离度量对指纹定位精度的提升较低,基于卡方距离度量的指纹定位精度明显优于另外两种方法。
关键词:K 最近邻;欧氏距离;马氏距离;卡方距离
中图分类号:TP391.4;P228.4 文献标识码:A 文章编号:2096-4706(2020)21-0020-04
Comparison of Fingerprint Location Algorithm Based on Different Measurements
HAN Yuchen,ZHONG Chen ,XU Jinxiu,LIU Qinghua
(School of Space Information and Surveying Engineering,Anhui University of Science and Technology,Huainan 232001,China)
Abstract:In the fingerprint location weighted K-nearest neighbor algorithm,the traditional Euclidean distance measurement principle is simple,but it will ignore the difference between different characteristics of the sample unit,making the location error larger. In order to overcome the shortcomings of the Euclidean distance,Mahalanobis distance and Chi-square distance are used to replace them,and the weighted K-nearest neighbor algorithm is combined to compare the positioning accuracy. The test results show that,under the condition of taking the same K value,the accuracy of fingerprint location based on Mahalanobis distance measurement is less improved, and the accuracy of fingerprint location based on Chi-square distance measurement is obviously better than the other two distances.
Keywords:K-nearest neighbor;Euclidean distance;Mahalanobis distance;Chi-square distance
基金项目:安徽省教育厅(高等学校省级质量工程项目)(2017jyxm1243)
参考文献:
[1] 邓中亮,尹露,唐诗浩,等. 室内定位关键技术综述 [J].导航定位与授时,2018(3):14-23.
[2] 裴凌,刘东辉,钱久超. 室内定位技术与应用综述 [J]. 导航定位与授时,2017,4(3):1-10.
[3] 李博心,祁浩然,鲁祥,等. 室内定位算法与技术综述 [J].电子元器件与信息技术,2020,4(1):47-50.
[4] YOUSSEF M. Horus:A WLAN-based Indoor LocationDeterminationSystem [D].Alexandria:Alexandria University,2004.
[5] 王培良,张婷,肖英杰. 改进指纹库精度下的室内定位算法研究 [J]. 电子技术应用,2018,44(10):97-101+105.
[6] 倪巍,王宗欣. 基于接收信号强度测量的室内定位算法 [J]. 复旦学报(自然科学版),2004(1):72-76.
[7] 孙瑜,范平志. 射频识别技术及其在室内定位中的应用 [J]. 计算机应用,2005(5):1205-1208.
[8] NIU J W,WANG B W,SHU L,et al. ZIL:An Energy-Efficient Indoor Localization System Using ZigBee Radio to Detect WiFiFingerprints [J].IEEE Journal on Selected Areas in Communications,2015,33(7):1431-1442.
[9] 王星星,丛思安. 室内定位研究方法综述 [J]. 软件导刊,2019,18(9):9-12.
[10] 厚丹妮. 基于深度学习的位置指纹室内定位算法研究 [D]. 西安:西安电子科技大学,2019.
[11] 丁义,杨建. 欧式距离与标准化欧式距离在k 近邻算法中的比较 [J]. 软件,2020,41(10):135-136+140.
[12] 陶峥,王洪玉. 基于卡方距离改进的WLAN 室内定位算法 [J]. 计算机技术与发展,2016,26(9):50-55.
[13] 谢红,赵洪野. 基于卡方距离度量的改进KNN 算法 [J].应用科技,2015,42(1):10-14.
作者简介:韩雨辰(1996—),男,汉族,安徽阜阳人,硕士在读,研究方向:室内定位。