By Topic

A Bayesian learning approach to linear system identification with missing data

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Pillonetto, G. ; Dipt. di Ing. dell''Inf., Univ. of Padova, Padova, Italy ; Chiuso, A.

We propose a novel nonparametric approach to ARMAX identification with missing data relying upon recent work on predictor estimation via Gaussian regression. The Bayesian setup allows one to compute explicitly an input-output marginal density where the model dependence has been integrated out. This turns out to be a key step in facilitating the imputation of missing variables. Thus, this approach has the advantage that no classical ¿model selection¿ (or model order estimation) has to be performed. Model ¿complexity¿ is described by means of hyperparameters which are estimated as part of the identification procedure. The new approach is shown to perform better than standard prediction error methods (PEM), also when the full data set is made available to the latter, in terms of both predictive capability on new data and accuracy in predictor coefficients reconstruction.

Published in:

Decision and Control, 2009 held jointly with the 2009 28th Chinese Control Conference. CDC/CCC 2009. Proceedings of the 48th IEEE Conference on

Date of Conference:

15-18 Dec. 2009