摘要
为了改善无线传感器网络节点定位的精确度,提出一种基于相关向量机的传感器节点定位方法.收集RSSI信号,采用核主成分分析提取其中重要的定位特征,采用相关向量机对特征向量和位置信息之间的关系进行拟合,建立传感器节点定位的回归函数.利用仿真实验分析传感器节点的定位效果,结果表明,基于相关向量机的传感器节点定位方法可以获得高精度的传感器节点定位结果,节点定位的实时性较好.
In order to improve wireless sensor network node positioning accuracy, a new localization method of sensor nodes based on relevance vector machine is proposed in this paper. RSSI signals are collected and kernel principal component analysis is used to extract important location features, and relevance vector machine is used to fit the relationship between feature vector and location information in which cuckoo search algorithm is used to optimize parameters to establish fitting function of sensor nodes localization, the simulation experiment is used to analyze sensor node localization effect. The results show that the proposed algorithm can get higher accuracy of sensor node localization results, and node localization has good real-time.
出处
《内蒙古师范大学学报（自然科学汉文版）》
CAS
北大核心
2016年第6期784-787,共4页
Journal of Inner Mongolia Normal University(Natural Science Edition)
基金
广西高等学校科学技术研究项目(2013YB295)
广西高等教育教改工程项目(2013JGA314)
关键词
无线传感器
网络节点
定位
相关向量机
核主成分分析
wireless sensor
network node
location
relevance vector machine
kernel principal component analysis
