eprintid: 9560
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/95/60
datestamp: 2023-11-09 16:36:12
lastmod: 2023-11-09 16:36:12
status_changed: 2023-11-09 16:29:17
type: article
metadata_visibility: show
creators_name: Javvad ur Rehman, M.
creators_name: Dass, S.C.
creators_name: Asirvadam, V.S.
title: A weighted likelihood criteria for learning importance densities in particle filtering
ispublished: pub
keywords: Dynamical systems; Maximum principle; Monte Carlo methods; Nonlinear dynamical systems; State space methods, Ensemble Kalman Filter; Expectation-maximization algorithms; Gaussian Mixture Model; Nonlinear state space models; Particle filter, Kalman filters
note: cited By 7
abstract: Selecting an optimal importance density and ensuring optimal particle weights are central challenges in particle-based filtering. In this paper, we provide a two-step procedure to learn importance densities for particle-based filtering. The first stage importance density is constructed based on ensemble Kalman filter kernels. This is followed by learning a second stage importance density via weighted likelihood criteria. The importance density is learned by fitting Gaussian mixture models to a set of particles and weights. The weighted likelihood learning criteria ensure that the second stage importance density is closer to the true filtered density, thereby improving the particle filtering procedure. Particle weights recalculated based on the latter density are shown to mitigate particle weight degeneracy as the filtering procedure propagates in time. We illustrate the proposed methodology on 2D and 3D nonlinear dynamical systems. © 2018, The Author(s).
date: 2018
publisher: Springer International Publishing
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048610027&doi=10.1186%2fs13634-018-0557-5&partnerID=40&md5=dc6f02a8759dd89aeac0e498b0e7fcf3
id_number: 10.1186/s13634-018-0557-5
full_text_status: none
publication: Eurasip Journal on Advances in Signal Processing
volume: 2018
number: 1
refereed: TRUE
issn: 16876172
citation:   Javvad ur Rehman, M. and Dass, S.C. and Asirvadam, V.S.  (2018) A weighted likelihood criteria for learning importance densities in particle filtering.  Eurasip Journal on Advances in Signal Processing, 2018 (1).   ISSN 16876172