Tampere University of Technology

TUTCRIS Research Portal

State Estimation for a Class of Piecewise Affine State-Space Models

Research output: Contribution to journalArticleScientificpeer-review

Standard

State Estimation for a Class of Piecewise Affine State-Space Models. / Rui, Rafael; Ardeshiri, Tohid; Nurminen, Henri; Bazanella, Alexandre; Gustafsson, Fredrik.

In: IEEE Signal Processing Letters, Vol. 24, No. 1, 01.2017, p. 61-65.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Rui, R, Ardeshiri, T, Nurminen, H, Bazanella, A & Gustafsson, F 2017, 'State Estimation for a Class of Piecewise Affine State-Space Models', IEEE Signal Processing Letters, vol. 24, no. 1, pp. 61-65. https://doi.org/10.1109/LSP.2016.2633624

APA

Rui, R., Ardeshiri, T., Nurminen, H., Bazanella, A., & Gustafsson, F. (2017). State Estimation for a Class of Piecewise Affine State-Space Models. IEEE Signal Processing Letters, 24(1), 61-65. https://doi.org/10.1109/LSP.2016.2633624

Vancouver

Rui R, Ardeshiri T, Nurminen H, Bazanella A, Gustafsson F. State Estimation for a Class of Piecewise Affine State-Space Models. IEEE Signal Processing Letters. 2017 Jan;24(1):61-65. https://doi.org/10.1109/LSP.2016.2633624

Author

Rui, Rafael ; Ardeshiri, Tohid ; Nurminen, Henri ; Bazanella, Alexandre ; Gustafsson, Fredrik. / State Estimation for a Class of Piecewise Affine State-Space Models. In: IEEE Signal Processing Letters. 2017 ; Vol. 24, No. 1. pp. 61-65.

Bibtex - Download

@article{b886265456674e339e9a57cc3ef33881,
title = "State Estimation for a Class of Piecewise Affine State-Space Models",
abstract = "We propose a filter for piecewise affine state-space models. In each filtering recursion, the true filtering posterior distribution is a mixture of truncated normal distributions. The proposed filter approximates the mixture with a single normal distribution via moment matching. The proposed algorithm is compared with the extended Kalman filter (EKF) in a numerical simulation, where the proposed method obtains, on average, better root mean square error than the EKF.",
keywords = "piecewise affine, state-space models, nonlinear filtering, Kalman filtering",
author = "Rafael Rui and Tohid Ardeshiri and Henri Nurminen and Alexandre Bazanella and Fredrik Gustafsson",
year = "2017",
month = "1",
doi = "10.1109/LSP.2016.2633624",
language = "English",
volume = "24",
pages = "61--65",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers",
number = "1",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - State Estimation for a Class of Piecewise Affine State-Space Models

AU - Rui, Rafael

AU - Ardeshiri, Tohid

AU - Nurminen, Henri

AU - Bazanella, Alexandre

AU - Gustafsson, Fredrik

PY - 2017/1

Y1 - 2017/1

N2 - We propose a filter for piecewise affine state-space models. In each filtering recursion, the true filtering posterior distribution is a mixture of truncated normal distributions. The proposed filter approximates the mixture with a single normal distribution via moment matching. The proposed algorithm is compared with the extended Kalman filter (EKF) in a numerical simulation, where the proposed method obtains, on average, better root mean square error than the EKF.

AB - We propose a filter for piecewise affine state-space models. In each filtering recursion, the true filtering posterior distribution is a mixture of truncated normal distributions. The proposed filter approximates the mixture with a single normal distribution via moment matching. The proposed algorithm is compared with the extended Kalman filter (EKF) in a numerical simulation, where the proposed method obtains, on average, better root mean square error than the EKF.

KW - piecewise affine

KW - state-space models

KW - nonlinear filtering

KW - Kalman filtering

U2 - 10.1109/LSP.2016.2633624

DO - 10.1109/LSP.2016.2633624

M3 - Article

VL - 24

SP - 61

EP - 65

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 1

ER -