针对基于接收信号强度指示(RSSI)的K最近邻(KNN)算法在室内定位精度较低的问题,提出一种改进的KNN—三角形内点(KNN—PIT)室内定位算法。根据室内空间结构特征,建立具有类标号的位置指纹库。引入虚拟参考点,利用PIT原理进一步约束目标点的定位区域,自适应地使用定位算法进行定位。综合运用高斯滤波、均值滤波技术,降低离线和在线阶段的信号随机误差。结果表明:改进后的KNN—PIT定位算法可以更好地估计用户的实际位置,降低定位误差,定位精度提高12.5%。
Aiming at problem of KNN algorithm low precision of indoor positioning based on RSSI,an improved KNN—PIT indoor positioning algorithm is put forward. According to structure feature of indoor space,establish location fingerprint database which has class labels. Introduce virtual reference points,use theory of PIT to further constrain localization area of target point,use positioning algorithm adaptively to carry out positioning.Comprehensively use Gauss filtering and mean filtering to reduce random errors of signal in online and offline stages. Results show that the improved KNN—PIT algorithm can better estimate the user's actual location,and decrease significantly localization errors,positioning precision is improved by 12. 5 %.