Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Receding Horizon Prediction by Bayesian Combination of Multiple Predictors

Ståhl, Fredrik LU and Johansson, Rolf LU orcid (2012) 51st IEEE Conference on Decision and Control, 2012 p.5278-5285
Abstract
This paper presents a novel online approach of merging multiple different predictors of time-varying dynamics into a single optimized prediction. Different predictors are merged by recursive weighting into a single prediction using regularized optimization. The approach is evaluated on two different cases of data with shifting dynamics; one example of prediction using several approximate models of a linear system and one case of glucose prediction on a non-linear physiologically based simulated type I diabetes data using several parallel linear predictors. The performance of the combined prediction significantly reduced the total prediction error compared to each

predictor in each example.
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proc. 51st IEEE Conf. Decision and Control (CDC 2012), December 10-13, 2012. Maui, Hawaii, USA
pages
8 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
51st IEEE Conference on Decision and Control, 2012
conference location
Maui, Hawaii, United States
conference dates
2012-12-10 - 2012-12-13
external identifiers
  • wos:000327200405097
  • scopus:84874258116
ISSN
0191-2216
project
DIAdvisor
language
English
LU publication?
yes
id
6ed27d98-78f0-4dee-9b55-d89e585c99f8 (old id 3402585)
date added to LUP
2016-04-01 14:00:07
date last changed
2022-01-27 22:17:04
@inproceedings{6ed27d98-78f0-4dee-9b55-d89e585c99f8,
  abstract     = {{This paper presents a novel online approach of merging multiple different predictors of time-varying dynamics into a single optimized prediction. Different predictors are merged by recursive weighting into a single prediction using regularized optimization. The approach is evaluated on two different cases of data with shifting dynamics; one example of prediction using several approximate models of a linear system and one case of glucose prediction on a non-linear physiologically based simulated type I diabetes data using several parallel linear predictors. The performance of the combined prediction significantly reduced the total prediction error compared to each<br/><br>
predictor in each example.}},
  author       = {{Ståhl, Fredrik and Johansson, Rolf}},
  booktitle    = {{Proc. 51st IEEE Conf. Decision and Control (CDC 2012), December 10-13, 2012. Maui, Hawaii, USA}},
  issn         = {{0191-2216}},
  language     = {{eng}},
  pages        = {{5278--5285}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Receding Horizon Prediction by Bayesian Combination of Multiple Predictors}},
  url          = {{https://lup.lub.lu.se/search/files/3717227/3806436.pdf}},
  year         = {{2012}},
}