基于自适应权重的RFID室内定位算法

RFID Indoor Positioning Algorithm Based on Adaptive Weight

针对复杂环境下室内定位稳定性差和误差大的问题,提出基于自适应权重的RFID室内定位算法.根据误差分布特性,采用马氏距离构造基于正态分布的权重函数,自适应赋予每个样本不同的权重;对加权最小二乘支持向量机建立惩罚系数和核函数参数组合的目标函数;采用粒子群优化算法(PSO)优化最优目标函数,利用混沌粒子的随机性和遍历性,将混沌寻优的最优解代替粒子群寻优的最优解,避免陷入局部最优,提高定位精度.仿真实验结果表明,该算法在室内定位中精度更高,定位更稳定.

Aiming at the problem of poor indoor positioning stability and large error in a complex environment,this study proposed an RFID indoor positioning algorithm based on adaptive weight.According to the error distribution characteristics,a weight function was constructed based on a normal distribution with Mahalanobis distance to adaptively assign different weights to each sample.The weighted least squares support vector machine was used to establish the objective function of the combination of the penalty coefficient and kernel function parameters.The particle swarm optimization algorithm(PSO)was used to optimize the optimal objective function,and the randomness and ergodicity of chaotic particles were used to replace the optimal solution of particle swarm optimization with chaos optimization and to avoid falling into local optimum,thus increasing the positioning accuracy.Simulation experiment results showed that the proposed algorithm had higher accuracy and more stable positioning in indoor positioning.