基于改进粒子滤波的RFID室内目标定位算法

针对于LANDMARC算法的RFID室内定位精度受传输路径影响严重,直接采用粒子滤波自适应性差的问题,提出一种基于改进粒子滤波的RFID室内定位算法。该算法首先利用极限学习机(ELM)拟合阅读器接收信号强度与标签距离之间的非线性关系,构建信号传输模型,筛选邻近标签集;然后采用自适应学习因子优化粒子滤波过程,提高粒子全局寻优能力和收敛速度。仿真实验结果表明,该算法能够有效实现待测标签的RFID室内定位,且定位精度较高,收敛速度较快。

RFID indoor target positioning algorithm based on improved particle filter

LANDMARC algorithm is widely used in RFID indoor positioning,the accuracy of which is seriously affected by the transmission path,and the direct use of particle filter has poor adaptability.Therefore,a RFID indoor positioning algorithm based on improved particle filter is proposed in this paper.The algorithm first uses extreme learning machine(ELM)to fit the nonlinear relationship between the reader’s received signal intensity and tag distance.Signal transmission model is constructed and the neighbor tag set is filtered,and then,the adaptive learning factor is used to improve the particle filter process to improve the global optimization ability and convergence speed of particles.The simulation results show that the algorithm can effectively realize RFID indoor positioning of the tag,and has high positioning accuracy and fast convergence speed.