基于LANDMARC的最近邻居改进算法

基于LANDMARC的最近邻居改进算法 An Improved Nearest Neighbors Algorithm Based on LANDMARC 邹学玉 ZOU Xueyu 1 first-author 韩付伟 HAN Fuwei 1 长江大学电信学院 长江大学电信学院 School of Electronics Information,Yangtze University School of Electronics Information,Yangtze University 对基于动态主动式射频识别标定的定位识别（LANDMARC）室内定位系统算法进行了研究,针对现有LANDMARC室内定位系统算法最近邻居数量固定导致优良的最近邻居丢失、不良最近邻居引入的问题,提出了一种改进的最近邻居算法（K-nearest neighbor algorithm,KNN）.该算法利用待测标签的预估位置,划定最近邻居的选择区域,然后根据选择区域内参考标签与预估位置能级差选择最近邻居.MATLAB仿真结果表明,在同等条件下的新算法定位精度提高了9.8%,最大误差降低了21.8%. This paper studied the algorithm of LANDMARC indoor positioning system.For fixed number of nearest neighbors caused losing of the good nearest neighbors and introducing of the bad nearest neighbors,an improved KNN（K-nearest neighbor algorithm） algorithm is proposed.The algorithm determines the selection area of the nearest neighbors by the estimated position of the undetermined tag and selects the nearest neighbors according to the RSSI difference.Under the same conditions,simulations using MATLAB show that the new algorithm can improve the positioning accuracy by 9.8% and reduce the maximum positioning error by 21.8%. 基于动态主动式射频识别标定的定位识别（LANDMARC） 最近邻居算法 参考标签 射频识别（RFID） 室内定位 location identification based on dynamic active RFID calibration（LANDMARC） KNN algorithm reference tag radio frequency identification（RFID） indoor positioning 10.14188/j.1671-8836.2013.03.007 TP391.44 湖北省教育厅重点（D20091204）资助项目 2013-03-01 2021-04-01 3 59