论文部分内容阅读
针对传播路径损耗模型的参数,极易受室内障碍物等环境因素影响,导致定位精度低的问题.利用RBF(径向基函数)神经网络算法替代损耗模型,拟合RSSI(接收信号强度)值与距离的关系.采集室内RSSI值和其对应的距离值的实测数据,利用实测数据训练RBF神经网络,建立RSSI-距离拟合模型;利用拟合模型将经过处理的RSSI值转换为距离值,并将距离值按从小到大排序;取前3个离定位节点较近的固定节点的信息,进行加权质心定位计算.研究结果表明:RBF算法的定位精度比路径传播损耗模型算法提高了34.5%,且略高于BP算法的定位精度.在相同的室内环境下,RBF算法能更好地克服环境因素对距离计算的干扰,提高室内定位的精度和稳定性.
The parameters of the propagation path loss model are easily affected by environmental factors such as indoor obstacles, which leads to the problem of low positioning accuracy. The RBF (Radial Basis Function) neural network algorithm is used to replace the loss model and the RSSI (Received Signal Strength) And the distance between the RSSI value and the corresponding distance value of the measured data collection, the use of measured data training RBF neural network, the establishment of RSSI-distance fitting model; using the fitting model will be processed RSSI value is converted to the distance value, And the distance values are sorted from small to large. The first three fixed nodes near the positioning node are used to calculate the weighted centroid position.The results show that the positioning accuracy of RBF algorithm is increased by 34.5% compared with the path propagation loss model algorithm, , And slightly higher than that of BP algorithm.Under the same indoor environment, RBF algorithm can better overcome the interference of environmental factors to distance calculation and improve the accuracy and stability of indoor positioning.