后验Monte Carlo Gaussian采样粒子滤波WSN定位  

Posterior Monte Carlo Gaussian resampling particle filter algorithm for WSN localization

作　　者：陈婷[1] 刘海燕[1] 熊曾刚[2] 

机构地区：[1]北京信息职业技术学院计算机工程系,北京100018 [2]湖北工程学院计算机与信息科学学院,湖北孝感432000

出　　处：《计算机应用研究》2016年第7期2113-2116,2185,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61370092;51409290)

摘　　要：环境因素导致无线传感器网络定位存在噪声影响,实质上是非平滑的非线性问题。针对传统粒子滤波算法在处理该问题时精度不高的缺点,提出一种基于后验泊松分布的Monte Carlo Gaussian重采样粒子滤波算法的无线传感器网络定位算法。基于粒子滤波算法,借鉴扩展卡尔曼滤波算法采用近似后验高斯分布思想,设计了后验泊松分布Monte Carlo Gaussian重采样粒子滤波器。采用该滤波器设计实现了无线传感器网络定位算法,解决了非平滑非线性的噪声干扰定位问题。分别对滤波器和定位算法的性能进行了对比仿真实验,结果验证了所提算法的有效性。Localization in wireless sensor network existed noise effects by environmental factors caused, which was essentially nonlinear problem of non smooth. In view of the traditional particle filter algorithm in dealing with the issue of the disadvantage of low accuracy, this paper proposed the posterior Monte Carlo Gaussian resampling particle filter algorithm for WSN localization. Firstly, based on particle filter algorithm, it designed the posterior Poisson distribution Monte Carlo Gaussian re-sampling particle filter with the thought of extended Calman filter algorithm and the approximate posterior distribution. Secondly, It used the filter design to implement wireless sensor network localization algorithm, solved the problem of non smooth nonlinear noise interference location. Finally, simulation experiment was carried respectively on the filter performance and the localization accuracy comparation. The results verify the effectiveness of the proposed algorithm.

关 键 词：后验概率 MONTE Carlo GAUSSIAN 粒子滤波 无线传感器网络 定位 

分 类 号：TN915.07[电子电信—通信与信息系统]