Backward hidden Markov chain for outlier-robust filtering and fixed-interval smoothing

B. Ait-El-Fquih; Cedric Gouy-Pailler

doi:10.1109/ICASSP.2013.6638716

Conference papers

Backward hidden Markov chain for outlier-robust filtering and fixed-interval smoothing

B. Ait-El-Fquih ¹ Cedric Gouy-Pailler ¹

1 LADIS - Laboratoire d'analyse des données et d'intelligence des systèmes

DM2I - Département Métrologie Instrumentation & Information : DRT/LIST/DM2I

Abstract : This paper addresses the problem of recursive estimation of a process in presence of outliers among the observations. It focuses on deriving robust approximate Kalman-like backward filtering and backward-forward fixed-interval smoothing algorithms in the context of linear hidden Markov chain with heavy-tailed measurement noise. The proposed algorithms are derived based on the backward Markovianity of the model as well as the variational Bayesian approach. In a simulation design, our algorithms are shown to outperform the classical Kalman filter in the presence of outliers.

Keywords : Variational bayesian approaches Algorithms Bayesian networks Markov processes Signal processing Statistics Variational bayes Robust smoothing Robust filtering Recursive estimation Markovian model Hidden Markov chains Fixed-interval smoothing

Document type :

Conference papers

Domain :

Statistics [stat] / Methodology [stat.ME]

Engineering Sciences [physics] / Signal and Image processing

Complete list of metadata

https://hal-cea.archives-ouvertes.fr/cea-01830771
Contributor : Léna Le Roy <>
Submitted on : Thursday, July 5, 2018 - 1:12:51 PM
Last modification on : Monday, March 30, 2020 - 2:36:03 PM

Backward hidden Markov chain for outlier-robust filtering and fixed-interval smoothing

Identifiers

Collections

Citation

Export

Metrics

116

Backward hidden Markov chain for outlier-robust filtering and fixed-interval smoothing

Identifiers

Collections

Citation

Export

Share

Metrics

116