Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs

Rupam Kalyan Chakraborty; Geethu Joseph; Chandra R. Murthy

doi:10.1109/ICASSP48485.2024.10446534

Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs

Rupam Kalyan Chakraborty^*, Geethu Joseph, Chandra R. Murthy^*

^*Corresponding author for this work

Signal Processing Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

1 Downloads (Pure)

Abstract

We consider the problem of jointly estimating the states and sparse inputs of a linear dynamical system using noisy low-dimensional observations. We exploit the underlying sparsity in the inputs using fictitious sparsity-promoting Gaussian priors with unknown variances (as hyperparameters). We develop two Bayesian learning-based techniques to estimate states and inputs: sparse Bayesian learning and variational Bayesian inference. Through numerical simulations, we illustrate that our algorithms outperform the conventional Kalman filtering based algorithm and other state-of-the-art sparsity-driven algorithms, especially in the low-dimensional measurement regime.

Original language	English
Title of host publication	2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
Publisher	IEEE
Pages	13431-13435
Number of pages	5
ISBN (Electronic)	9798350344851
DOIs	https://doi.org/10.1109/ICASSP48485.2024.10446534
Publication status	Published - 2024
Event	49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Seoul, Korea, Republic of Duration: 14 Apr 2024 → 19 Apr 2024

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Country/Territory	Korea, Republic of
City	Seoul
Period	14/04/24 → 19/04/24

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Gaussian prior
Kalman smoothing
robust filtering
sparse Bayesian learning
variational Bayesian inference

Access to Document

10.1109/ICASSP48485.2024.10446534

Bayesian_Learning-Based_Kalman_Smoothing_For_Linear_Dynamical_Systems_With_Unknown_Sparse_InputsFinal published version, 1.01 MB

Cite this

Chakraborty, R. K., Joseph, G., & Murthy, C. R. (2024). Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs. In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings (pp. 13431-13435). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). IEEE. https://doi.org/10.1109/ICASSP48485.2024.10446534

Chakraborty, Rupam Kalyan ; Joseph, Geethu ; Murthy, Chandra R. / Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. IEEE, 2024. pp. 13431-13435 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{d43d4d9c2c71470f84e09115647c3443,

title = "Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs",

abstract = "We consider the problem of jointly estimating the states and sparse inputs of a linear dynamical system using noisy low-dimensional observations. We exploit the underlying sparsity in the inputs using fictitious sparsity-promoting Gaussian priors with unknown variances (as hyperparameters). We develop two Bayesian learning-based techniques to estimate states and inputs: sparse Bayesian learning and variational Bayesian inference. Through numerical simulations, we illustrate that our algorithms outperform the conventional Kalman filtering based algorithm and other state-of-the-art sparsity-driven algorithms, especially in the low-dimensional measurement regime.",

keywords = "Gaussian prior, Kalman smoothing, robust filtering, sparse Bayesian learning, variational Bayesian inference",

author = "Chakraborty, {Rupam Kalyan} and Geethu Joseph and Murthy, {Chandra R.}",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 ; Conference date: 14-04-2024 Through 19-04-2024",

year = "2024",

doi = "10.1109/ICASSP48485.2024.10446534",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "IEEE",

pages = "13431--13435",

booktitle = "2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings",

address = "United States",

}

Chakraborty, RK , Joseph, G & Murthy, CR 2024, Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs. in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, IEEE, pp. 13431-13435, 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, Seoul, Korea, Republic of, 14/04/24. https://doi.org/10.1109/ICASSP48485.2024.10446534

Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs. / Chakraborty, Rupam Kalyan ; Joseph, Geethu; Murthy, Chandra R.
2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. IEEE, 2024. p. 13431-13435 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs

AU - Chakraborty, Rupam Kalyan

AU - Joseph, Geethu

AU - Murthy, Chandra R.

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2024

Y1 - 2024

N2 - We consider the problem of jointly estimating the states and sparse inputs of a linear dynamical system using noisy low-dimensional observations. We exploit the underlying sparsity in the inputs using fictitious sparsity-promoting Gaussian priors with unknown variances (as hyperparameters). We develop two Bayesian learning-based techniques to estimate states and inputs: sparse Bayesian learning and variational Bayesian inference. Through numerical simulations, we illustrate that our algorithms outperform the conventional Kalman filtering based algorithm and other state-of-the-art sparsity-driven algorithms, especially in the low-dimensional measurement regime.

AB - We consider the problem of jointly estimating the states and sparse inputs of a linear dynamical system using noisy low-dimensional observations. We exploit the underlying sparsity in the inputs using fictitious sparsity-promoting Gaussian priors with unknown variances (as hyperparameters). We develop two Bayesian learning-based techniques to estimate states and inputs: sparse Bayesian learning and variational Bayesian inference. Through numerical simulations, we illustrate that our algorithms outperform the conventional Kalman filtering based algorithm and other state-of-the-art sparsity-driven algorithms, especially in the low-dimensional measurement regime.

KW - Gaussian prior

KW - Kalman smoothing

KW - robust filtering

KW - sparse Bayesian learning

KW - variational Bayesian inference

UR - http://www.scopus.com/inward/record.url?scp=85195372449&partnerID=8YFLogxK

U2 - 10.1109/ICASSP48485.2024.10446534

DO - 10.1109/ICASSP48485.2024.10446534

M3 - Conference contribution

AN - SCOPUS:85195372449

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 13431

EP - 13435

BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings

PB - IEEE

T2 - 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024

Y2 - 14 April 2024 through 19 April 2024

ER -

Chakraborty RK , Joseph G, Murthy CR. Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs. In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. IEEE. 2024. p. 13431-13435. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP48485.2024.10446534

Bayesian learning-based Kalman smoothing for linear dynamical systems with unknown sparse inputs

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this