Abstract
We introduce and formalize the multilevel classification problem, in which each category can be subdivided into different levels. We analyze the framework in a Bayesian setting using Normal class conditional densities. Within this framework, a natural monotonicity hint converts the problem into a nonlinear programming task, with non-linear constraints. We present Monte Carlo and gradient based techniques for addressing this task, and show the results of simulations. Incorporation of monotonicity yields a systematic improvement in performance.
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
Y. Abu-Mostafa. Hints. Neural Computation, 4(7):639–671, 1995.
Agency for Healthcare Research and Quality. Clinical classifications software. fact sheet. http://www.ahrq.gov/data/hcup/ccsfact.htm , Internet Citation.
C. Bishop. Neural Networks for Pattern Recognition. Clarendon Pr., Oxford, 1995.
D. Rixen, J. H. Siegel, and H. P. Friedman. ”Sepsis/SIRS” physiologic classification, severity stratification, relation to cytokine elaboration and outcome prediction in posttrauma critical illness. Journal of Trauma, 41:581–598, 1996.
J. H. Siegel, D. Rixen, and H. P. Friedman. Physiological classification and stratification of illness severity of posttrauma’ sepsis’ patients as a basis for randomization of clinical trials. Journal of Endotoxin Research, 2(17):177–188, 1995.
J. Smith and S. Chang. Multi-stage classification of images from features and related text. In 4th Europe EDLOS Workshop, Aug 1997.
M. Taylor. Discovering multi-level classification rules in platelet transfusion databases. Ph.D. Dissertation Proposal, University of Maryland, December 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Magdon-Ismail, M., Chen, HC.(., Abu-Mostafa, Y.S. (2002). The Multilevel Classification Problem and a Monotonicity Hint. In: Yin, H., Allinson, N., Freeman, R., Keane, J., Hubbard, S. (eds) Intelligent Data Engineering and Automated Learning — IDEAL 2002. IDEAL 2002. Lecture Notes in Computer Science, vol 2412. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45675-9_61
Download citation
DOI: https://doi.org/10.1007/3-540-45675-9_61
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44025-3
Online ISBN: 978-3-540-45675-9
eBook Packages: Springer Book Archive