Online Updating of Conditional Linear Gaussian Bayesian Networks

Anders L Madsen, Kristian G Olesen, Frank Jensen, Per Henriksen, Thomas M Larsen, Jørn M Møller
Proceedings of The 11th International Conference on Probabilistic Graphical Models, PMLR 186:97-108, 2022.

Abstract

This paper presents a method for online updating of conditional distributions in Bayesian network models with both discrete and continuous variables. The method extends known procedures for updating discrete conditional probability distributions with techniques to cope with conditional Gaussian density functions. The method has a solid foundation for known cases and may be generalised by a heuristic scheme for fractional updating when discrete parents are not known. A fading mechanism is described to prevent the system being too conservative as cases accumulate over long time periods. The effect of the online updating is illustrated by an application to predict the number of waiting patients at the emergency department at Aalborg University Hospital.

Cite this Paper

BibTeX
@InProceedings{pmlr-v186-madsen22a, title = {Online Updating of Conditional Linear Gaussian Bayesian Networks}, author = {Madsen, Anders L and Olesen, Kristian G and Jensen, Frank and Henriksen, Per and Larsen, Thomas M and M{\o}ller, J{\o}rn M}, booktitle = {Proceedings of The 11th International Conference on Probabilistic Graphical Models}, pages = {97--108}, year = {2022}, editor = {Salmerón, Antonio and Rumı́, Rafael}, volume = {186}, series = {Proceedings of Machine Learning Research}, month = {05--07 Oct}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v186/madsen22a/madsen22a.pdf}, url = {https://proceedings.mlr.press/v186/madsen22a.html}, abstract = {This paper presents a method for online updating of conditional distributions in Bayesian network models with both discrete and continuous variables. The method extends known procedures for updating discrete conditional probability distributions with techniques to cope with conditional Gaussian density functions. The method has a solid foundation for known cases and may be generalised by a heuristic scheme for fractional updating when discrete parents are not known. A fading mechanism is described to prevent the system being too conservative as cases accumulate over long time periods. The effect of the online updating is illustrated by an application to predict the number of waiting patients at the emergency department at Aalborg University Hospital. } }
Endnote
%0 Conference Paper %T Online Updating of Conditional Linear Gaussian Bayesian Networks %A Anders L Madsen %A Kristian G Olesen %A Frank Jensen %A Per Henriksen %A Thomas M Larsen %A Jørn M Møller %B Proceedings of The 11th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2022 %E Antonio Salmerón %E Rafael Rumı́ %F pmlr-v186-madsen22a %I PMLR %P 97--108 %U https://proceedings.mlr.press/v186/madsen22a.html %V 186 %X This paper presents a method for online updating of conditional distributions in Bayesian network models with both discrete and continuous variables. The method extends known procedures for updating discrete conditional probability distributions with techniques to cope with conditional Gaussian density functions. The method has a solid foundation for known cases and may be generalised by a heuristic scheme for fractional updating when discrete parents are not known. A fading mechanism is described to prevent the system being too conservative as cases accumulate over long time periods. The effect of the online updating is illustrated by an application to predict the number of waiting patients at the emergency department at Aalborg University Hospital.
APA
Madsen, A.L., Olesen, K.G., Jensen, F., Henriksen, P., Larsen, T.M. & Møller, J.M.. (2022). Online Updating of Conditional Linear Gaussian Bayesian Networks. Proceedings of The 11th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 186:97-108 Available from https://proceedings.mlr.press/v186/madsen22a.html.

Related Material