Student's t-Filters for Noise Scale Estimation
(2019) In IEEE Signal Processing Letters 26(2). p.352-356- Abstract
In this letter, we analyze certain student's t-filters for linear Gaussian systems with misspecified noise covariances. It is shown that under appropriate conditions, the filter both estimates the state and re-scales the noise covariance matrices in a Kullback-Leibler optimal fashion. If the noise covariances are misscaled by a common scalar, then the re-scaling is asymptotically exact. We also compare the student's t-filter scale estimates to the maximum-likelihood estimates. Simulations demonstrating the results on the Wiener velocity model are provided.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/813ac6a1-6ba1-4171-ae94-72f26db15525
- author
- Tronarp, Filip LU ; Karvonen, Toni and Sarkka, Simo
- publishing date
- 2019
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Kalman filtering, model misspecification, noise covariance estimation, student's t-filtering
- in
- IEEE Signal Processing Letters
- volume
- 26
- issue
- 2
- article number
- 8606947
- pages
- 5 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85060530856
- ISSN
- 1070-9908
- DOI
- 10.1109/LSP.2018.2889440
- language
- English
- LU publication?
- no
- id
- 813ac6a1-6ba1-4171-ae94-72f26db15525
- date added to LUP
- 2023-08-20 22:45:56
- date last changed
- 2023-10-30 08:46:49
@article{813ac6a1-6ba1-4171-ae94-72f26db15525, abstract = {{<p>In this letter, we analyze certain student's t-filters for linear Gaussian systems with misspecified noise covariances. It is shown that under appropriate conditions, the filter both estimates the state and re-scales the noise covariance matrices in a Kullback-Leibler optimal fashion. If the noise covariances are misscaled by a common scalar, then the re-scaling is asymptotically exact. We also compare the student's t-filter scale estimates to the maximum-likelihood estimates. Simulations demonstrating the results on the Wiener velocity model are provided.</p>}}, author = {{Tronarp, Filip and Karvonen, Toni and Sarkka, Simo}}, issn = {{1070-9908}}, keywords = {{Kalman filtering; model misspecification; noise covariance estimation; student's t-filtering}}, language = {{eng}}, number = {{2}}, pages = {{352--356}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Signal Processing Letters}}, title = {{Student's t-Filters for Noise Scale Estimation}}, url = {{http://dx.doi.org/10.1109/LSP.2018.2889440}}, doi = {{10.1109/LSP.2018.2889440}}, volume = {{26}}, year = {{2019}}, }