A best lag size of minimum variance FIR smoothers

Bo Kyu Kwon; Ji Woong Choi; Jung Hun Park; Soohee Han; Wook Hyun Kwon

doi:10.1109/LSP.2009.2014118

A best lag size of minimum variance FIR smoothers

Bo Kyu Kwon, Ji Woong Choi, Jung Hun Park, Soohee Han, Wook Hyun Kwon

Department of Electrical Engineering and Computer Science

Seoul National University

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

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.

Original language	English
Article number	4797895
Pages (from-to)	308-311
Number of pages	4
Journal	IEEE Signal Processing Letters
Volume	16
Issue number	4
DOIs	https://doi.org/10.1109/LSP.2009.2014118
State	Published - 2009

Bibliographical note

Funding Information:
Manuscript received August 07, 2008; revised December 15, 2008. Current version published March 06, 2009. This work was supported in part by the Ministry of Knowledge Economy, Korea, and by the second stage of the Brain Korea 21 Project in 2008. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Yuriy V. Zakharov. B. K. Kwon and W. H. Kwon are with the School of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea. J.-W. Choi is with Marvell Semiconductor, Inc., Santa Clara, CA 95054 USA. J. H. Park and S. Han are with the BK21 School for Creative Engineering Design of Next Generation Mechanical and Aerospace Systems, Seoul National University, Seoul, Korea (e-mail: [email protected]). Digital Object Identifier 10.1109/LSP.2009.2014118

Keywords

Best lag size
Minimum variance FIR smoother

Access to Document

10.1109/LSP.2009.2014118

Cite this

@article{3b84092ad22447029837020a1a13570c,

title = "A best lag size of minimum variance FIR smoothers",

abstract = "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.",

keywords = "Best lag size, Minimum variance FIR smoother",

author = "Kwon, {Bo Kyu} and Choi, {Ji Woong} and Park, {Jung Hun} and Soohee Han and Kwon, {Wook Hyun}",

note = "Funding Information: Manuscript received August 07, 2008; revised December 15, 2008. Current version published March 06, 2009. This work was supported in part by the Ministry of Knowledge Economy, Korea, and by the second stage of the Brain Korea 21 Project in 2008. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Yuriy V. Zakharov. B. K. Kwon and W. H. Kwon are with the School of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea. J.-W. Choi is with Marvell Semiconductor, Inc., Santa Clara, CA 95054 USA. J. H. Park and S. Han are with the BK21 School for Creative Engineering Design of Next Generation Mechanical and Aerospace Systems, Seoul National University, Seoul, Korea (e-mail: [email protected]). Digital Object Identifier 10.1109/LSP.2009.2014118",

year = "2009",

doi = "10.1109/LSP.2009.2014118",

language = "English",

volume = "16",

pages = "308--311",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - A best lag size of minimum variance FIR smoothers

AU - Kwon, Bo Kyu

AU - Choi, Ji Woong

AU - Park, Jung Hun

AU - Han, Soohee

AU - Kwon, Wook Hyun

N1 - Funding Information: Manuscript received August 07, 2008; revised December 15, 2008. Current version published March 06, 2009. This work was supported in part by the Ministry of Knowledge Economy, Korea, and by the second stage of the Brain Korea 21 Project in 2008. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Yuriy V. Zakharov. B. K. Kwon and W. H. Kwon are with the School of Electrical Engineering and Computer Science, Seoul National University, Seoul, Korea. J.-W. Choi is with Marvell Semiconductor, Inc., Santa Clara, CA 95054 USA. J. H. Park and S. Han are with the BK21 School for Creative Engineering Design of Next Generation Mechanical and Aerospace Systems, Seoul National University, Seoul, Korea (e-mail: [email protected]). Digital Object Identifier 10.1109/LSP.2009.2014118

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - Best lag size

KW - Minimum variance FIR smoother

UR - http://www.scopus.com/inward/record.url?scp=84867430726&partnerID=8YFLogxK

U2 - 10.1109/LSP.2009.2014118

DO - 10.1109/LSP.2009.2014118

M3 - Article

AN - SCOPUS:84867430726

SN - 1070-9908

VL - 16

SP - 308

EP - 311

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 4

M1 - 4797895

ER -

A best lag size of minimum variance FIR smoothers

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this