Non-informative Bayesian dispersion particle filter
In this research paper, we attempt to introduce a new algorithm for filtering a state-space model. The observations of this algorithm follow an exponential dispersion model. The paper focuses here on the inclusion of non-informative prior knowledge in parameter estimation on nonlinear state-space m...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Sciences and Technology, University Center Abdelhafid Boussouf, Mila
2024-01-01
|
| Series: | Journal of Innovative Applied Mathematics and Computational Sciences |
| Subjects: | |
| Online Access: | https://jiamcs.centre-univ-mila.dz/index.php/jiamcs/article/view/1717 |
| _version_ | 1797349555396673536 |
|---|---|
| author | Ibrahim Sadok |
| author_facet | Ibrahim Sadok |
| author_sort | Ibrahim Sadok |
| collection | DOAJ |
| description |
In this research paper, we attempt to introduce a new algorithm for filtering a state-space model. The observations of this algorithm follow an exponential dispersion model. The paper focuses here on the inclusion of non-informative prior knowledge in parameter estimation on nonlinear state-space models using an improper uniform prior measure. Therefore, a new particle filter is introduced. A conventional particle filter (PF) produces an incorrect sample from a discrete approximation distribution. This new algorithm is a regularized continuous distribution method that is obtained with the exponential dispersion model. A necessary and sufficient condition for the existence and convergence of the non-informative Bayesian estimator of dispersion parameters is established. This methodology extends the classical PF implemented by this new estimation method for the exponential dispersion model framework using a non-informative Bayesian approach. In order to evaluate the performance of the proposed algorithm, a case study with simulations and microscopic image restoration is carried out. The results exhibit a great performance improvement from the proposed approach
|
| first_indexed | 2024-03-08T12:32:00Z |
| format | Article |
| id | doaj.art-142777cd4bb74b5a8e8f6024943b4f8f |
| institution | Directory Open Access Journal |
| issn | 2773-4196 |
| language | English |
| last_indexed | 2024-03-08T12:32:00Z |
| publishDate | 2024-01-01 |
| publisher | Institute of Sciences and Technology, University Center Abdelhafid Boussouf, Mila |
| record_format | Article |
| series | Journal of Innovative Applied Mathematics and Computational Sciences |
| spelling | doaj.art-142777cd4bb74b5a8e8f6024943b4f8f2024-01-21T21:51:09ZengInstitute of Sciences and Technology, University Center Abdelhafid Boussouf, MilaJournal of Innovative Applied Mathematics and Computational Sciences2773-41962024-01-013210.58205/jiamcs.v3i2.1717Non-informative Bayesian dispersion particle filterIbrahim Sadok0Department of Mathematics and Computer Science, Faculty of Exact Sciences, University of Bechar, Algeria In this research paper, we attempt to introduce a new algorithm for filtering a state-space model. The observations of this algorithm follow an exponential dispersion model. The paper focuses here on the inclusion of non-informative prior knowledge in parameter estimation on nonlinear state-space models using an improper uniform prior measure. Therefore, a new particle filter is introduced. A conventional particle filter (PF) produces an incorrect sample from a discrete approximation distribution. This new algorithm is a regularized continuous distribution method that is obtained with the exponential dispersion model. A necessary and sufficient condition for the existence and convergence of the non-informative Bayesian estimator of dispersion parameters is established. This methodology extends the classical PF implemented by this new estimation method for the exponential dispersion model framework using a non-informative Bayesian approach. In order to evaluate the performance of the proposed algorithm, a case study with simulations and microscopic image restoration is carried out. The results exhibit a great performance improvement from the proposed approach https://jiamcs.centre-univ-mila.dz/index.php/jiamcs/article/view/1717Dispersion exponential modelParticle filternon-informative Bayesian priormicroscopic image restoration |
| spellingShingle | Ibrahim Sadok Non-informative Bayesian dispersion particle filter Journal of Innovative Applied Mathematics and Computational Sciences Dispersion exponential model Particle filter non-informative Bayesian prior microscopic image restoration |
| title | Non-informative Bayesian dispersion particle filter |
| title_full | Non-informative Bayesian dispersion particle filter |
| title_fullStr | Non-informative Bayesian dispersion particle filter |
| title_full_unstemmed | Non-informative Bayesian dispersion particle filter |
| title_short | Non-informative Bayesian dispersion particle filter |
| title_sort | non informative bayesian dispersion particle filter |
| topic | Dispersion exponential model Particle filter non-informative Bayesian prior microscopic image restoration |
| url | https://jiamcs.centre-univ-mila.dz/index.php/jiamcs/article/view/1717 |
| work_keys_str_mv | AT ibrahimsadok noninformativebayesiandispersionparticlefilter |