无人机数据传输缺失数据拟合算法  

Missing Data Fitting Algorithm in UAV Data Transmission

作　　者：王娜娜 徐辉[1] WANG Na-na;XU Hui(Computer Science and Engineering,Anhui University of Science and Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001

出　　处：《电脑知识与技术》2020年第13期270-272,共3页Computer Knowledge and Technology

基　　金：国家自然科学基金资助项目(61404001,61306046);国家自然科学基金面上项目(61371025);安徽省高校省级自然科学研究重大项目(KJ20148D12);淮南市科技计划(2013A4011)。

摘　　要：在无人机和地面站通信交互的过程中,由于各方面因素,例如频率不同步、传输延时等,可能会造成无人机采集到的数据在传输期间发生错误,导致地面站接收到的数据有部分丢失。文章提出一种梯度下降优化算法--梯度下降自适应学习率算法(RMSProp with NAG,RMSPN),对缺失数据集进行曲线拟合,得到丢失数据的近似值,对缺失数据集进行填补。实验结果证明了该方法曲线拟合效果良好,估计值与实际值误差较小,算法可行性高。During the communication andinteraction between the UAV and the ground station,due to various factors,such as fre⁃quency unsynchronization,transmission delay,etc.,the data collected by the UAVmay cause errors,resulting in data should be re⁃ceived by the ground station has lost.In this paper,a gradient descent optimization algorithm,RMSProp with NAG(RMSPN),is proposed to perform curve fitting on missing datasets to obtain approximate values of missing data,and to fill in missing datasets.The experimental results show that the curve fitting effect of the method is good,the error between the estimated value and the actu⁃al value is small,and the algorithm is highly feasible.

关 键 词：无人机 数据缺失 梯度下降优化算法 数据集 曲线拟合 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]