Online data processing: comparison of Bayesian regularized particle filters
نویسندگان
چکیده
The aim of this paper is to compare three regularized particle filters in an online data processing context. We carry out the comparison in terms of hidden states filtering and parameters estimation, considering a Bayesian paradigm and a univariate stochastic volatility model. We discuss the use of an improper prior distribution in the initialization of the filtering procedure and show that the Regularized Auxiliary Particle Filter (R-APF) outperforms the Regularized Sequential Importance Sampling (R-SIS) and the Regularized Sampling Importance Resampling (R-SIR). Key-words: Online data processing, Bayesian estimation, regularized particle filters, stochastic volatility model ∗ Department of Economics, University of Brescia † INRIA Futurs, Projet select, Université Paris-Sud in ria -0 01 38 00 7, v er si on 3 4 M ar 2 00 8 Traitement de données en temps réel : comparaison de filtres particulaires bayésiens régularisés Résumé : L’objectif de ce travail est de comparer trois filtres particulaires régularisés pour le traitement de données en temps réel. Les trois filtres sont évalués pour leurs capacités à reconstituer les états latents du système et à estimer les paramètres du modèle. Nous considérons le paradigme bayésien et le modèle à volatilité stochastique. Nous montrons que les performances du filtre particulaire auxiliaire sont meilleures que celles des filtres particulaires classiques d’échantillonnage préférentiel séquentiel. Mots-clés : Traitement de données en temps réel, estimation bayésienne, filtres particulaires régularisés, modèle à volatilité stochastique in ria -0 01 38 00 7, v er si on 3 4 M ar 2 00 8 Comparison of Bayesian regularized particle filters 3
منابع مشابه
A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking
Increasingly, for many application areas, it is becoming important to include elements of nonlinearity and non-Gaussianity in order to model accurately the underlying dynamics of a physical system. Moreover, it is typically crucial to process data on-line as it arrives, both from the point of view of storage costs as well as for rapid adaptation to changing signal characteristics. In this paper...
متن کاملRao-Blackwellised Particle Filtering for Dynamic Bayesian Networks
Particle filters (PFs) are powerful samplingbased inference/learning algorithms for dynamic Bayesian networks (DBNs). They allow us to treat, in a principled way, any type of probability distribution, nonlinearity and non-stationarity. They have appeared in several fields under such names as “condensation”, “sequential Monte Carlo” and “survival of the fittest”. In this paper, we show how we ca...
متن کاملLocal Kernels that Approximate Bayesian Regularization and Proximal Operators
In this work, we broadly connect kernel-based filtering (e.g. approaches such as the bilateral filters and nonlocal means, but also many more) with general variational formulations of Bayesian regularized least squares, and the related concept of proximal operators. The latter set of variational/Bayesian/proximal formulations often result in optimization problems that do not have closed-form so...
متن کاملAn Online Learning-based Framework for Tracking
We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. However, these solutions can be very sensitive to model mismatches. In this paper...
متن کاملVision-Based Guitarist Fingering Tracking Using a Bayesian Classifier and Particle Filters
This paper presents a vision-based method for tracking guitar fingerings played by guitar players from stereo cameras. We propose a novel framework for colored finger markers tracking by integrating a Bayesian classifier into particle filters, with the advantages of performing automatic track initialization and recovering from tracking failures in a dynamic background. ARTag (Augmented Reality ...
متن کامل