基于高斯混合模型的无线传感器网络定位算法  

Location Algorithm Based on GaussianMixture Model in Wireless Sensor Network

作　　者：方省 罗引 曹家 徐楠 蒋水宾 郝艳妮 FANG Xing;LUO Yin;CAO Jia;XU Nan;JIANG Shuibin;HAO Yanni(School of Economics and Management,Tianjin University,Tianjin 300072,China;Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China;Beijing Wenge Technology Co.,Ltd.,Beijing 100000,China)

机构地区：[1]天津大学经济与管理学院,天津300072 [2]中国科学院自动化研究所,北京100190 [3]北京中科闻歌科技股份有限公司,北京100000

出　　处：《吉林大学学报（理学版）》2022年第3期713-720,共8页Journal of Jilin University:Science Edition

基　　金：国家重点研发计划“科技冬奥”重点专项基金(批准号:2020YFF0305300);国家自然科学基金创新研究群体项目(批准号:71621002).

摘　　要：针对距离误差对定位结果的影响,提出一种基于高斯混合模型的无线传感器网络定位算法.该算法将高斯混合模型方法引入到无线传感器网络的定位问题中,通过高斯混合模型分析找出误差较大的距离信息并将其剔除,对剩余距离信息使用三边测量定位法进行定位求解,同时结合加权定位算法进行位置估计.仿真实验结果表明,改进算法能提高定位精度,且定位结果更稳定.Aiming at the influence of distance error on the location results,we proposed a location algorithm based on Gaussian mixture model(GMM)in wireless sensor network(WSN).In this algorithm,the GMM method was introduced into the location problem of WSN.The distance information with large error was found by using the analysis of GMM and eliminated.The remaining distance information was solved by trilateral measurement location method,and the position was estimated combined with wighted location algorithm.Simulation results show that the improved algorithm can improve positioning accuracy and the positioning results are more stable.

关 键 词：高斯混合模型 无线传感器网络 定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TN92[自动化与计算机技术—计算机科学与技术]