Abstract
When modeling technical processes, the training data regularly come from test plans, to reduce the number of experiments and to save time and costs. On the other hand, this leads to unobserved combinations of the input variables. In this article it is shown, that these unobserved configurations might lead to un-trainable parameters. Afterwards a possible design criterion is introduced, which avoids this drawback. Our approach is tested to model a welding process. The results show, that hybrid Bayesian networks are able to deal with yet unobserved in- and output data.
This work was funded by the “German Research Association” (DFG), Collaborative research center (SFB) 396, project-parts C1 and C3. Only the authors are responsible for the content of this article.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Larry B. Barrentine. Introduction to Design of Experiments: A Simplified Approach. ASQ Quality Press, Milwaukee, 1999.
R. Cowell. Advanced inference in bayesian networks. In M.I. Jordan, editor, Learning in graphical models, pages 27–49. MIT Press, Cambridge, Massachusetts, 1999.
R. Deventer, J. Denzler, and H. Niemann. Non-linear modeling of a production process by hybrid Bayesian Networks. In Werner Horn, editor, ECAI 2000 (Berlin), pages 576–580. IOS Press, August 2000.
F.V. Jensen. An introduction to Bayesian networks. UCL Press, 1996.
O. Kreis and Ph. Hein. Manufacturing system for the integrated hydroforming, trimming and welding of sheet metal pairs. Journal of Materials Processing Technology, 115:49–54, 2001.
Oliver Kreis. Integrierte Fertigung — Verfahrensintegration durch Innenhochdruck-Umformen, Trennen und Laserstrahlschweißen in einem Werkzeug sowie ihre tele-und multimediale Präsentation. PhD thesis, Universität Erlangen-Nürnberg, Meisenbach, Bamberg, 2002. http://www.integrierte-fertigung.de.
S.L. Lauritzen. Propagation of probabilities, means, and variances in mixed graphical association models. Journal of the American Statistical Association, Vol. 87(420):1098–1108, December 1992.
S.L. Lauritzen and F. Jensen. Stable Local Computation with Conditional Gaussian Distributions. Technical Report R-99-2014, Aalborg University, Department of Mathematical Sciences, September 1999.
Uri Lerner, Eran Segal, and Daphne Koller. Exact inference in networks with discrete children of continuous parents. In Uncertainty in Artificial Intelligence: Proceedings of the Seventeenth Conference (UAI-2001), pages 319–328, San Francisco, CA, 2001. Morgan Kaufmann Publishers.
Douglas C. Montgomery. Design and Analysis of Experiments. Wiley, New York, fifth edition edition, 2000.
Kevin P. Murphy. Inference and Learning in Hybrid Bayesian Networks. Technical Report CSD-98-990, University of California, Computer Science Division (EECS), January 1998.
Kevin P. Murphy. A variational approximation for bayesian networks with discrete and continuous latent variables. In Kathryn Blackmond Laskey and Henri Prade, editors, Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, San Francisco, 1999. Morgan Kaufmann Publishers Inc.
Kevin P. Murphy. The Bayes Net Toolbox for Matlab. Computing Science and Statistics, 33, 2001.
K.G. Olesen. Causal probabilistic networks with both discrete and continuous variables. IEEE Transaction on Pattern Analysis and Machine Intelligence, 3(15):275–279, 1993.
J. Pearl. Probabilistic reasoning in intelligent systems. Morgan Kaufmann Publishers, Inc., 1988. ISBN 0-934613-73-7.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Deventer, R., Denzler, J., Niemann, H., Kreis, O. (2003). Using Test Plans for Bayesian Modeling. In: Perner, P., Rosenfeld, A. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2003. Lecture Notes in Computer Science, vol 2734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45065-3_27
Download citation
DOI: https://doi.org/10.1007/3-540-45065-3_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40504-7
Online ISBN: 978-3-540-45065-8
eBook Packages: Springer Book Archive