Particle filter based MAP state estimation: A comparison

S. Saha; Y. Boers; J.N. Driessen; Pranab K. Mandal; Arunabha Bagchi

Particle filter based MAP state estimation: A comparison

S. Saha, Y. Boers, J.N. Driessen, Pranab K. Mandal, Arunabha Bagchi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

29 Citations (Scopus)

184 Downloads (Pure)

Abstract

MAP estimation is a good alternative to MMSE for certain applications involving nonlinear non Gaussian systems. Recently a new particle filter based MAP estimator has been derived. This new method extracts the MAP directly from the output of a running particle filter. In the recent past, a Viterbi algorithm based MAP sequence estimator has been developed. In this paper, we compare these two methods for estimating the current state and the numerical results show that the former performs better.

Original language	Undefined
Title of host publication	Proceedings of 12th International Conference on Information Fusion 2009
Publisher	International Society of Information Fusion
Pages	278-283
Number of pages	6
ISBN (Print)	978-0-9824438-0-4
Publication status	Published - 6 Jul 2009
Event	12th International Conference on Information Fusion, FUSION 2009 - Seattle, United States Duration: 6 Jul 2009 → 9 Jul 2009 Conference number: 12

Publication series

Name
Publisher	International Society of Information Fusion

Conference

Conference	12th International Conference on Information Fusion, FUSION 2009
Abbreviated title	FUSION 2009
Country/Territory	United States
City	Seattle
Period	6/07/09 → 9/07/09

Keywords

METIS-264049
Filter MAP
Bayesian point estimation
MSC-11K45
Particle filter
Sequential Monte Carlo
EWI-16113
IR-68153

Access to Document

Cite this

@inproceedings{abd6c8852ef743a7863423e08a89a165,

title = "Particle filter based MAP state estimation: A comparison",

abstract = "MAP estimation is a good alternative to MMSE for certain applications involving nonlinear non Gaussian systems. Recently a new particle filter based MAP estimator has been derived. This new method extracts the MAP directly from the output of a running particle filter. In the recent past, a Viterbi algorithm based MAP sequence estimator has been developed. In this paper, we compare these two methods for estimating the current state and the numerical results show that the former performs better.",

keywords = "METIS-264049, Filter MAP, Bayesian point estimation, MSC-11K45, Particle filter, Sequential Monte Carlo, EWI-16113, IR-68153",

author = "S. Saha and Y. Boers and J.N. Driessen and Mandal, {Pranab K.} and Arunabha Bagchi",

year = "2009",

month = jul,

day = "6",

language = "Undefined",

isbn = "978-0-9824438-0-4",

publisher = "International Society of Information Fusion",

pages = "278--283",

booktitle = "Proceedings of 12th International Conference on Information Fusion 2009",

note = "12th International Conference on Information Fusion, FUSION 2009 ; Conference date: 06-07-2009 Through 09-07-2009",

}

TY - GEN

T1 - Particle filter based MAP state estimation: A comparison

AU - Saha, S.

AU - Boers, Y.

AU - Driessen, J.N.

AU - Mandal, Pranab K.

AU - Bagchi, Arunabha

N1 - Conference code: 12

PY - 2009/7/6

Y1 - 2009/7/6

N2 - MAP estimation is a good alternative to MMSE for certain applications involving nonlinear non Gaussian systems. Recently a new particle filter based MAP estimator has been derived. This new method extracts the MAP directly from the output of a running particle filter. In the recent past, a Viterbi algorithm based MAP sequence estimator has been developed. In this paper, we compare these two methods for estimating the current state and the numerical results show that the former performs better.

AB - MAP estimation is a good alternative to MMSE for certain applications involving nonlinear non Gaussian systems. Recently a new particle filter based MAP estimator has been derived. This new method extracts the MAP directly from the output of a running particle filter. In the recent past, a Viterbi algorithm based MAP sequence estimator has been developed. In this paper, we compare these two methods for estimating the current state and the numerical results show that the former performs better.

KW - METIS-264049

KW - Filter MAP

KW - Bayesian point estimation

KW - MSC-11K45

KW - Particle filter

KW - Sequential Monte Carlo

KW - EWI-16113

KW - IR-68153

M3 - Conference contribution

SN - 978-0-9824438-0-4

SP - 278

EP - 283

BT - Proceedings of 12th International Conference on Information Fusion 2009

PB - International Society of Information Fusion

T2 - 12th International Conference on Information Fusion, FUSION 2009

Y2 - 6 July 2009 through 9 July 2009

ER -