摘要
在离线阶段对指纹库的构建采用多映射的数据结构,使每个采样点坐标对应同一AP的一个或多个RSSI信息值。在线匹配阶段,通过计算待定位点的RSSI信息与离线数据库的指纹信息的欧式距离,欧式距离值越小,说明两者的拟合程度越高,计算出两者拟合程度的最小值,以此找出与待定位点相关的指纹点。最后,使用WKNN匹配算法求出待定位点的估计坐标。
Multi-mapping data structure is applied to build fingerprint database at off-line phase to make every sampling point match the RSSI information value of the same AP. While at online matching stage, Euclidean distance between the RSSI information of the undetermined site and the fingerprint information of the off-line database is calculated. The smaller the Euclidean distance value, the higher the fitting degree, which indicates that the minimum value of the fitting degree can be obtained . Fingerprint points associated with undetermined sites can be identified accordingly. Finally, WKNN matching algorithm is used to calculate the estimated coordinates of undetermined sites.
作者
郭昕刚
胡朗
GUO Xingang;HU Lang(School of Computer Science & Engineering,Changchun University of Technology,Changchun 130012,China)
出处
《长春工业大学学报》
CAS
2018年第4期367-372,共6页
Journal of Changchun University of Technology
基金
吉林省重点科技攻关项目(20150204020SF)
关键词
室内定位
位置指纹定位
多映射数据结构
WKNN算法
indoor positioning;location fingerprint positioning;multi-mapping data structure;Weighted K Nearest Neighbor