Home
Grupo de investigación BISITE
  • EN EN
  • ES ES
University of Salamanca
  • Who are we?
  • Group
    • Team
    • Laboratories
    • Blog
  • R&D+i
    • Research Lines
    • Projects
      • Internationals
      • Nationals
      • Companies
      • Regionals
      • Educational innovation
      • Thematic networks
    • Publications
      • Journals
      • Books
      • Book chapters
      • Conferences
    • Technology Transfer
      • Partners
      • Platforms
  • Training
    • Masters
      • Master in 3D Printing
      • Master in Blockchain and Smart Contracts
      • Master in Digital Animation
      • Master in Digital Transformation
      • Master in Internet Security
      • Master in Smart Cities & Intelligent Buildings
      • Máster in the Internet of Things
      • Recursos TIC en el proceso de Enseñanza-Aprendizaje
    • Experts
      • Expert in 3D Printing
      • Expert in Blockchain and Smart Contracts
      • Expert in Digital Animation
      • Expert in Digital Transformation
      • Expert in Internet Security
      • Expert in Smart Cities & Intelligent Buildings
      • Expert in the Internet of Things
      • Experto en Gestión Laboral
      • Experto en Pericia Documental
    • MOOCs e4YOU
    • Campus-BISITE
  • Conferences
  • BISITE
  • Research
  • Publications

Effectiveness of Bayesian filters

Back
  • Research lines
  • Projects
    • Internationals
    • Nationals
    • Regionals
    • Companies
    • Educational innovation
    • Thematic networks
  • Publications
    • Journals
    • Books
    • Book chapters
    • Conferences
  • Intelectual Property Rights
Title:
Effectiveness of Bayesian filters.
Authors: 
Li, Tiancheng; Corchado Rodríguez, Juan M.; Bajo Pérez, Javier; Sun, Shudong; de Paz Santana, Juan F.
Journal:
Information Sciences. Volume 329, pp. 670-689. Elsevier.

Publication date: 
01 February 2016
ISSN: 
0020-0255
DOI
 10.1016/j.ins.2015.09.041

BibTex

@article { article,
title = {Effectiveness of Bayesian filters},
author = {Li, Tiancheng; Corchado Rodríguez, Juan M.; Bajo Pérez, Javier; Sun, Shudong; de Paz Santana, Juan F.},
journal = {Information Sciences},
publisher = {Elsevier},
volume = {329},
year = {2016}
}

XML

<article key='journals/Information/Li,/01 February 2016' mdate='01 February 2016'>
<author> Li</author>
<author> Tiancheng; Corchado Rodríguez</author>
<author> Juan M.; Bajo Pérez</author>
<author> Javier; Sun</author>
<author> Shudong; de Paz Santana</author>
<author> Juan F.</author>
<title> Effectiveness of Bayesian filters</title>
<pages> 670-689</pages>
<year> 2016</year>
<journal> Information Sciences</journal>
<ee> 10.1016/j.ins.2015.09.041</ee>
</article>
Evidences of quality:
JCR (2016): 4.832
COMPUTER SCIENCE, INFORMATION SYSTEMS: 7/146 (Q1)

A fundamental issue concerned the effectiveness of the Bayesian filter is raised.The observation-only (O2) inference is presented for dynamic state estimation.The "probability of filter benefit" is defined and quantitatively analyzed.Convincing simulations demonstrate that many filters can be easily ineffective. The general solution for dynamic state estimation is to model the system as a hidden Markov process and then employ a recursive estimator of the prediction-correction format (of which the best known is the Bayesian filter) to statistically fuse the time-series observations via models. The performance of the estimator greatly depends on the quality of the statistical mode assumed. In contrast, this paper presents a modeling-free solution, referred to as the observation-only (O2) inference, which infers the state directly from the observations. A Monte Carlo sampling approach is correspondingly proposed for unbiased nonlinear O2 inference. With faster computational speed, the performance of the O2 inference has identified a benchmark to assess the effectiveness of conventional recursive estimators where an estimator is defined as effective only when it outperforms on average the O2 inference (if applicable). It has been quantitatively demonstrated, from the perspective of information fusion, that a prior "biased" information (which inevitably accompanies inaccurate modelling) can be counterproductive for a filter, resulting in an ineffective estimator. Classic state space models have shown that a variety of Kalman filters and particle filters can easily be ineffective (inferior to the O2 inference) in certain situations, although this has been omitted somewhat in the literature.

Follow us


Links of interest

Contact

  • Edificio Multiusos I+D+i:
    Calle Espejo s/n, 37007, Salamanca, Spain

     

  • Phone: (+34) 923 294 400 ext. 1525
  • Fax: (+34) 923 294 514
  • Email: bisite@usal.es

Bisite Research Group

© Copyright 2022 | BISITE Research Group

  • Sitemap
  • Graphic Identity
If you continue browsing this website, you agree to our policies.
I agree to the site policies and terms of use
View policies