无线传感器网络中基于双支持向量回归的分布式定位算法

来源期刊:中南大学学报(自然科学版)2015年第8期

论文作者:郭戈 王其华

文章页码:2930 - 2937

关键词:无线传感器网络;双支持向量回归;定位算法;跳数

Key words:wireless sensor networks; twin support vector regression; localization algorithm; hop counts

摘    要:针对无线传感器网络中节点定位误差问题,提出一种基于双支持向量回归的分布式定位算法。在保持锚节点连通性的基础上,以锚节点跳数和位置信息为训练样本。结合拉格朗日法和KKT(Karush-Kuhn-Tuchker)条件,把原问题的优化转化为对偶形式,使用双支持向量回归技术确定跳数信息到节点间距离的映射函数。最后,采用最小二乘法估计待定位节点的位置,在不同锚节点和通信半径的情况下对传感器目标节点进行定位实验测试。实验结果表明:该方法减小了测量误差,能有效提高节点自身定位精度。

Abstract: Aimed at solving the problem of node localization error in wireless sensor networks, a novel approach to distributed localization was proposed based on twin support vector regression. By optimizing the connectivity of anchor nodes, the hop counts and the position information among anchor nodes were taken as training samples. Combined with the Lagrange method and Karush-Kuhn-Tuchker (KKT) conditions, the twin support vector regression was adopted to attain mapping model between hop count and distance by converting the optimization of the original problem into dual form. The least square method was used to obtain estimation position of unknown nodes. The experiments of sensor localization on different anchor nodes and the radius in WSN were carried out. The simulation results show that the location accuracy is improved by reducing measurement error.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号