Abstract
In previous chapters, we have introduced the Linguistic Decision Tree model and shown how this model can be used for classification and prediction. However, for some complex problems, good probability estimations can only be obtained by deep LDTs, which have low transparency. In such cases, how can we build a model which has a good probability estimation but which uses compact LDTs? In this chapter, two hybrid learning models are proposed combining the LDT model and the fuzzy Naive Bayes classifier. In the first model, an unlabeled instance is classified according to the Bayesian estimation given a single LDT. In the second model, a set of disjoint LDTs are used as Bayesian estimators. Experimental studies show that the first new hybrid models has both better accuracy and transparency when compared to fuzzy Naive Bayes and LDTs at shallow tree depths. The second model is shown to have equivalent performance to the LDT model.
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
Provost F., Domingos P.: Tree induction for probability-based ranking, Machine Learning, 52, pp. 199–215. (2003).
Blake C., Merz C. J.: UCI machine learning repository.
Jordan M. I.: Learning in Graphical Models, MIT Press. (1999).
Elkan C., Naive bayesian learning. Technical Report No. CS97-557, Department of Computer Science and Engineering, University of California, San Diego. (1997).
Pazzani M. J.: An iterative improvement approach for the discretization of numeric attributes in Bayesian classifiers, Proceedings of the 1st International Conference on Knowledge Discovery and Data Mining, pp. 228–233. (1995).
Yang Y., Webb G. I.: On why discretization works for naive-bayes classifiers, Proceedings of 16th Australian Joint Conference on Artificial Intelligence. (2003).
Hsu C. -N., Huang H. -J., Wong T. -T.: Implications of the Dirichlet assumption for discretization of continuous variables in Naive Bayesian classifiers, Machine Learning, 53, pp. 235–263. (2003).
Zhang H., Ling C. X.: A fundamental issue of Naive Bayes, Proceedings of 2003 Canadian Artificial Intelligence Conference. (2003).
Jeffrey R. C.: The Logic of Decision, Gordon & Breach Inc., New York. (1965).
Randon N. J., Lawry J.: Classification and query evaluation using modelling with words. Information Sciences, 176, pp. 438–464, (2006).
Hyndman R., Akram M.: Time series Data Library. Monash University. http://www-personal.buseco.monash.edu.au/~hyndman/TSDL/index.htm.
Gunn S. R.: Support vector machines for classification and regression. Technical Report of Departartment of Electronics and Computer Science, University of Southampton. (1998).
Konoenko I.: Semi-Naive Bayesian classifier, Proceedings of EWSL-91 6th European Workshop on Learning, Springer, pp. 206–219. (1991).
Randon N. J.: Fuzzy and Random Set Based Induction Algorithms, PhD Thesis, Department of Engineering Mathematics, University of Bristol. (2004).
Randon N. J., Lawry J.: Linguistic modelling using a semi-Naive Bayes framework, IPMU-2002, Annecy, France. (2002).
Randon N. J., Lawry J., Cluckie I. D.: Online learning for fuzzy Bayesian prediction, Soft Methods in Probability and Statistics (SMPS) Advances in Soft Computing, 6: pp. 405–412.
Quinlan J. R.: Induction of decision trees, Machine Learning, 1: pp. 81–106. (1986).
Quinlan J. R.:C4.5: Programs for Machine Learning, San Mateo: Morgan Kaufmann. (1993).
Ferri C., Flach P. A., Hernández-Orallo J.: Improving the AUC of probabilistic estimation trees, Proceedings of ECML-03, LNAI 2837, pp. 121–132. (2003).
Witten I. H., Frank E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, Morgan Kaufmann. (1999).
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2014 Zhejiang University Press, Hangzhou and Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Qin, Z., Tang, Y. (2014). Bayesian Methods Based on Label Semantics. In: Uncertainty Modeling for Data Mining. Advanced Topics in Science and Technology in China. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41251-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-41251-6_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41250-9
Online ISBN: 978-3-642-41251-6
eBook Packages: Computer ScienceComputer Science (R0)