基于RSS相关性的位置指纹室内定位方法

解决设备差异性造成的Wi-Fi信号强度不确定问题是位置指纹室内定位应用与推广的关键.一种基于设备间接收信号强度(Received Signal Strength,RSS)相关性的位置指纹室内定位方法被提出.以智能手机为用户终端,离线阶段,通过智能手机扫描的Wi-Fi信号强度信息,经过数据处理,筛选稳定的接入点(Access Point,AP),构建离线指纹数据库;在线定位阶段,对于实时获取的Wi-Fi信号强度信息,进行筛选处理后,挑选与离线指纹共同拥有的AP,并根据该AP集合,形成新的离线指纹和在线指纹.对离线指纹按RSS的大小降序排序;在线指纹,则以同一次序对RSS排序,然后利用皮尔逊相关系数和杰卡德相似系数,计算指纹相似度并排序,通过K最近邻(K-Nearest Neighbor,KNN)算法实现用户定位.实验表明该方法可有效解决设备差异性问题,并实现精确定位,平均定位误差达到1.7 m.

Received Signal Strength correlation based location fingerprint indoor localization

To solve the problem of Wi-Fi signal intensity uncertainty caused by the difference of equipment is the key to the application and popularization of location fingerprint indoor localization.An indoor localization method based on the correlation of Received Signal Strength (RSS) between devices is proposed.In the offline phase, the Wi-Fi signal intensity information is collected by the smartphone, and Access Point (AP) is selected through the data processing for constructing offline location fingerprint database.In the online phase, after selecting the Wi-Fi signal intensity information which is acquired in real time, the paper selects the APs which are shared with the off-line fingerprint, forming a new off-line fingerprint and online fingerprint based on the selected AP set.For off-line fingerprint , descend sorting by size of RSS, for online fingerprint, in the same order of RSS sort, then calculate the fingerprint similarity by the Pearson correlation coefficient and Jaccard coefficient of similarity, after sorting, use the K-Nearest Neighbor (KNN) to achieve the location of user.Experimental results show that the method can effectively solve the problem of equipment diversity and achieve accurate positioning with an average positioning error of 1.7 meters.