Title: | Copula-based convolution for fast point-mass prediction |
Authors: | Duník, Jindřich Straka, Ondřej Matoušek, Jakub Blasch, Erik |
Citation: | DUNÍK, J. STRAKA, O. MATOUŠEK, J. BLASCH, E. Copula-based convolution for fast point-mass prediction. Signal Processing, 2022, roč. 192, č. March 2022, s. 1-10. ISSN: 0165-1684 |
Issue Date: | 2022 |
Publisher: | Elsevier |
Document type: | článek article |
URI: | 2-s2.0-85118532393 http://hdl.handle.net/11025/47015 |
ISSN: | 0165-1684 |
Keywords in different language: | state estimation, nonlinear systems, Bayesian relations, convolution, point-mass filter, copula |
Abstract in different language: | This paper deals with the state estimation of the nonlinear stochastic dynamic discrete-in-time models by a numerical solution to the Bayesian recursive relations represented by the point-mass filter (PMF). In particular, emphasis is placed on the development of the fast convolution, which reduces computational complexity of the PMF prediction step by the orders of magnitude for models with a diagonal form of the dynamic equation. The copula-based convolution decomposes the joint conditional density into the marginal densities (allowing efficient prediction) and an easy-to-calculate copula density function. As a consequence, it has the linear growth of its computational complexity with the state dimension, which is in a contrast with the exponential growth of the standard convolution complexity in PMF methods. The proposed fast convolution is analysed and illustrated in a numerical study for a static example and a dynamic terrain-aided navigation scenario. An exemplary implementation of the proposed convolution is provided along with the paper. |
Rights: | Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © Elsevier |
Appears in Collections: | Články / Articles (KKY) OBD |
Files in This Item:
File | Size | Format | |
---|---|---|---|
article_SignalProcessing_DuStMaBl2022.pdf | 1,25 MB | Adobe PDF | View/Open Request a copy |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/47015
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.