Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

This chapter deals with the problem of non-linear and non-Gaussian states and parameters estimation using Bayesian methods. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF). In the current work, the authors consider two systems (biological model and power system) to perform evaluation of estimation algorithms. The results of the comparative studies show that the UKF provides a higher accuracy than the EKF due to the limited ability of EKF to accurately estimate the mean and covariance matrix of the estimated states through lineralization of the nonlinear process model. The results also show that the PF provides a significant improvement over the UKF because, unlike UKF, PF is not restricted by linear-Gaussian assumptions which greatly extends the range of problems that can be tackled.

Original languageEnglish
Title of host publicationHandbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications
PublisherIGI Global
Pages711-748
Number of pages38
Volume2-2
ISBN (Electronic)9781466644519
ISBN (Print)1466644508, 9781466644502
DOIs
Publication statusPublished - 31 Aug 2013

Fingerprint

State estimation
Kalman filters
Parameter estimation
Extended Kalman filters
Biological systems
Covariance matrix

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Mansouri, M., Mohamed-Seghir, M., Nounou, H., Nounou, M., & Abu-Rub, H. (2013). Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies. In Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications (Vol. 2-2, pp. 711-748). IGI Global. https://doi.org/10.4018/978-1-4666-4450-2.ch024

Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies. / Mansouri, Majdi; Mohamed-Seghir, Moustafa; Nounou, Hazem; Nounou, Mohamed; Abu-Rub, Haitham.

Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications. Vol. 2-2 IGI Global, 2013. p. 711-748.

Research output: Chapter in Book/Report/Conference proceedingChapter

Mansouri, M, Mohamed-Seghir, M, Nounou, H, Nounou, M & Abu-Rub, H 2013, Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies. in Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications. vol. 2-2, IGI Global, pp. 711-748. https://doi.org/10.4018/978-1-4666-4450-2.ch024
Mansouri M, Mohamed-Seghir M, Nounou H, Nounou M, Abu-Rub H. Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies. In Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications. Vol. 2-2. IGI Global. 2013. p. 711-748 https://doi.org/10.4018/978-1-4666-4450-2.ch024
Mansouri, Majdi ; Mohamed-Seghir, Moustafa ; Nounou, Hazem ; Nounou, Mohamed ; Abu-Rub, Haitham. / Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies. Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications. Vol. 2-2 IGI Global, 2013. pp. 711-748
@inbook{856bf1ad28c144d681984a97250f2a11,
title = "Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies",
abstract = "This chapter deals with the problem of non-linear and non-Gaussian states and parameters estimation using Bayesian methods. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF). In the current work, the authors consider two systems (biological model and power system) to perform evaluation of estimation algorithms. The results of the comparative studies show that the UKF provides a higher accuracy than the EKF due to the limited ability of EKF to accurately estimate the mean and covariance matrix of the estimated states through lineralization of the nonlinear process model. The results also show that the PF provides a significant improvement over the UKF because, unlike UKF, PF is not restricted by linear-Gaussian assumptions which greatly extends the range of problems that can be tackled.",
author = "Majdi Mansouri and Moustafa Mohamed-Seghir and Hazem Nounou and Mohamed Nounou and Haitham Abu-Rub",
year = "2013",
month = "8",
day = "31",
doi = "10.4018/978-1-4666-4450-2.ch024",
language = "English",
isbn = "1466644508",
volume = "2-2",
pages = "711--748",
booktitle = "Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications",
publisher = "IGI Global",

}

TY - CHAP

T1 - Non linear and non gaussian states and parameters estimation using bayesian methods-comparatives studies

AU - Mansouri, Majdi

AU - Mohamed-Seghir, Moustafa

AU - Nounou, Hazem

AU - Nounou, Mohamed

AU - Abu-Rub, Haitham

PY - 2013/8/31

Y1 - 2013/8/31

N2 - This chapter deals with the problem of non-linear and non-Gaussian states and parameters estimation using Bayesian methods. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF). In the current work, the authors consider two systems (biological model and power system) to perform evaluation of estimation algorithms. The results of the comparative studies show that the UKF provides a higher accuracy than the EKF due to the limited ability of EKF to accurately estimate the mean and covariance matrix of the estimated states through lineralization of the nonlinear process model. The results also show that the PF provides a significant improvement over the UKF because, unlike UKF, PF is not restricted by linear-Gaussian assumptions which greatly extends the range of problems that can be tackled.

AB - This chapter deals with the problem of non-linear and non-Gaussian states and parameters estimation using Bayesian methods. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF). In the current work, the authors consider two systems (biological model and power system) to perform evaluation of estimation algorithms. The results of the comparative studies show that the UKF provides a higher accuracy than the EKF due to the limited ability of EKF to accurately estimate the mean and covariance matrix of the estimated states through lineralization of the nonlinear process model. The results also show that the PF provides a significant improvement over the UKF because, unlike UKF, PF is not restricted by linear-Gaussian assumptions which greatly extends the range of problems that can be tackled.

UR - http://www.scopus.com/inward/record.url?scp=84945137903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945137903&partnerID=8YFLogxK

U2 - 10.4018/978-1-4666-4450-2.ch024

DO - 10.4018/978-1-4666-4450-2.ch024

M3 - Chapter

SN - 1466644508

SN - 9781466644502

VL - 2-2

SP - 711

EP - 748

BT - Handbook of Research on Novel Soft Computing Intelligent Algorithms: Theory and Practical Applications

PB - IGI Global

ER -