一种递增式物联网定位算法  

An Incremental Localization Algorithm for the Internet of Things

作　　者：郑久虎[1,2] 钱换延 

机构地区：[1]南京理工大学计算机科学与工程学院,江苏南京210094 [2]江苏经贸职业技术学院,江苏南京211168

出　　处：《金陵科技学院学报》2015年第4期14-17,共4页Journal of Jinling Institute of Technology

摘　　要：针对物联网中某些场景覆盖率不高的问题,通过可行加权最小二乘迭代加权消除递增过程中的累积误差,采用岭回归以避免节点共线造成估计误差过大的问题。计算过程中采用实际计算的残差作为加权最小二乘的权值,使得算法更符合实际部署情况。同时采用岭回归方法消除了共线影响,可使方法获得较高的定位精度更高。Aiming at the lower coverage rate of some scenes in the Internet of things,the paper eliminates the cumulative errors in the increasing process through the feasible weighted least squares iterative weighting method,and on the basis the ridge regression is used to avoid the large estimation errors caused by collinear nodes.Since the calculation of the residual in the actual calculation is adopted as the weight of the weighted least squares,the algorithm is in more accordance with the actual deployment.At the same time,the ridge regression method is used to eliminate the effect of collinear.Therefore,the method can obtain higher localization accuracy.

关 键 词：物联网 定位 可行加权最小二乘 岭回归 

分 类 号：TN929.5[电子电信—通信与信息系统] TP391.44[电子电信—信息与通信工程]