首页|Data-Based Filters for Non-Gaussian Dynamic Sys-tems With Unknown Output Noise Covariance
Data-Based Filters for Non-Gaussian Dynamic Sys-tems With Unknown Output Noise Covariance
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
国家科技期刊平台
NETL
NSTL
万方数据
This paper proposes linear and nonlinear filters for a non-Gaussian dynamic system with an unknown nominal covari-ance of the output noise.The challenge of designing a suitable fil-ter in the presence of an unknown covariance matrix is addressed by focusing on the output data set of the system.Considering that data generated from a Gaussian distribution exhibit ellipsoidal scattering,we first propose the weighted sum of norms(SON)clustering method that prioritizes nearby points,reduces distant point influence,and lowers computational cost.Then,by intro-ducing the weighted maximum likelihood,we propose a semi-def-inite program(SDP)to detect outliers and reduce their impacts on each cluster.Detecting these weights paves the way to obtain an appropriate covariance of the output noise.Next,two filtering approaches are presented:a cluster-based robust linear filter using the maximum a posterior(MAP)estimation and a cluster-based robust nonlinear filter assuming that output noise distribu-tion stems from some Gaussian noise resources according to the ellipsoidal clusters.At last,simulation results demonstrate the effectiveness of our proposed filtering approaches.
Data-based filtermaximum likelihood estimationunknown covarianceweighted maximum likelihood estimationweighted sum-of-norms clustering
Elham Javanfar、Mehdi Rahmani
展开 >
Department of Electrical Engineering, Imam Khomeini International University, Qazvin 3414896818, Iran
国家科技期刊平台
NSTL
万方数据
