A Best Lag Size of Minimum Variance FIR Smoothers

In this paper, we argue that the lag size of half a moving horizon of the minimum variance finite impulse response (MVFIR) smoother is not generally best in the sense of the estimation error variance even though it has been believed to be optimal for a simple input/output (I/O) model with correlated...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2009-04, Vol.16 (4), p.307-310
Main Authors: Bo Kyu Kwon, Bo Kyu Kwon, Ji-Woong Choi, Ji-Woong Choi, Jung Hun Park, Jung Hun Park, Soohee Han, Soohee Han, Wook Hyun Kwon, Wook Hyun Kwon
Format: Article
Language:English
Subjects:
Asymmetry
Best lag size
Delay effects
Delay estimation
Errors
Estimation error
Finite impulse response filter
Horizon
Impulse response
Kalman filters
Kernel
Mathematical analysis
Mathematical model
Mathematical models
minimum variance FIR smoother
Robustness
Scalars
State estimation
State-space methods
Studies
Variance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we argue that the lag size of half a moving horizon of the minimum variance finite impulse response (MVFIR) smoother is not generally best in the sense of the estimation error variance even though it has been believed to be optimal for a simple input/output (I/O) model with correlated data. For a more general analysis, a state space model is considered in this paper. It is shown via numerical example that the dependency of the lag size on the minimum estimation error variance is asymmetric around half a moving horizon and varies with model parameters. In the case of a scalar system, the best lag size is represented in a closed-form. Some hints on a numerical method are presented for a more general vector system. Considering the lag size as well as the estimation error, we also propose a new performance criterion that puts a penalty on the large lag size while making the estimation error small.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2009.2014118