基于PSO优化LSSVR的三维WSN节点定位方法  

Three-dimensional WSN node localization method based on LSSVR optimized by PSO algorithm

作　　者：张烈平[1,2] 陈鸣[2] 季文军[2] 

机构地区：[1]桂林理工大学广西矿冶与环境科学实验中心,广西桂林541004 [2]桂林理工大学机械与控制工程学院,广西桂林541004

出　　处：《中国科技论文》2014年第1期24-27,44,共5页China Sciencepaper

基　　金：广西自然科学基金项目(桂科自0991252);广西高等学校科学研究重点资助项目(桂教科研201202ZD051)

摘　　要：提出了一种基于粒子群优化最小二乘支持向量回归机的三维无线传感器网络节点定位方法。该方法首先运用最小二乘支持向量回归机构建三维节点定位模型,再利用粒子群优化算法对最小二乘支持向量回归机核函数参数和规则化参数寻优。然后,根据若干虚拟节点定位的预测位置与实际位置的均方差构造粒子群算法适应度函数,通过有限次建模参数迭代寻优获得最小二乘支持向量回归机全局最优参数。最后,返回回归模型中进行定位计算,实现节点定位。仿真结果表明,所提出的方法与最小二乘和最小二乘支持向量回归机定位方法相比,可以提高节点定位精度。A localization method based on LSSVR optimized by particle swarm optimization （PSO）algorithm is proposed in this paper.Firstly,the three-dimensional（3D）node localization model is built through least squares support vector regression （LSS-VR）and the kernel function parameters and the regularization parameters are optimized by PSO algorithm.Then,the fitness function of the particle swarm optimization algorithm is constructed according to the mean square error of a number of virtual nodes from the predicted position and their actual position,and the global optimal parameters of LSSVR is acquired through limit-ed modeling parameters iterative searching method.Finally,the LSSVR optimized by PSO algorithm is used to realize the node localization.The simulation results show that the localization accuracy of the proposed algorithm is superior to that of least square （LS）and LSSVR methods.

关 键 词：无线传感器网络 三维节点定位 粒子群算法 最小二乘支持向量回归机 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置] TN929.5[自动化与计算机技术—控制科学与工程]