A Non-Parametric Scheme for Identifying Data Characteristic Based on Curve Similarity Matching

作     者：Quanbo Ge Yang Cheng Hong Li Ziyi Ye Yi Zhu Gang Yao Quanbo Ge;Yang Cheng;Hong Li;Ziyi Ye;Yi Zhu;Gang Yao

作者机构：School of AutomationNanjing University of Information Science&TechnologyJiangsu Provincial University Key Laboratory of Big Data Analysis and Intelligent SystemsNanjing University of Information Science&Technologyand the Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET)Nanjing University of Information Science&TechnologyNanjing 210044China School of Department of Logistics EngineeringShanghai Maritime UniversityShanghai 201306China China Classification Society Nantong OfficeNantong 226006China Chinese Flight Test EstablishmentXi’an 710089China School of MathematicsTsinghua UniversityBeijing 100084China School of AutomationNanjing University of Information Science&TechnologyNanjing 210044China Department of Logistics EngineeringShanghai Maritime UniversityShanghai 201306China IEEE 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2024年第11卷第6期

页      面：1424-1437页

核心收录：

学科分类：08[工学] 082503[工学-航空宇航制造工程] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 

基　　金：supported by the National Natural Science Foundation of China(62033010) Qing Lan Project of Jiangsu Province(R2023Q07)。 

主　　题：Curve similarity matching Gaussian-like noise non-parametric scheme parzen window. 

摘      要：For accurately identifying the distribution charac-teristic of Gaussian-like noises in unmanned aerial vehicle(UAV)state estimation,this paper proposes a non-parametric scheme based on curve similarity matching.In the framework of the pro-posed scheme,a Parzen window(kernel density estimation,KDE)method on sliding window technology is applied for roughly esti-mating the sample probability density,a precise data probability density function(PDF)model is constructed with the least square method on K-fold cross validation,and the testing result based on evaluation method is obtained based on some data characteristic analyses of curve shape,abruptness and symmetry.Some com-parison simulations with classical methods and UAV flight exper-iment shows that the proposed scheme has higher recognition accuracy than classical methods for some kinds of Gaussian-like data,which provides better reference for the design of Kalman filter(KF)in complex water environment.