Abstract
We introduce the notion of naive evidential classifier. This classifier, which has a structure mirroring the naive Bayes classifier, is based on the Transferable Belief Model and uses mass assignments as its uncertainty model. This new method achieves more robust inferences, mainly by explicitly modeling imprecision when data are in little amount or are imprecise. After introducing the model and its inference process based on Smet’s generalized Bayes theorem (GBT), we specify some possible methods to learn its parameters, based on the Imprecise Dirichlet Model (IDM) or on predictive belief functions. Some experimental results on an agronomic application are then given and evaluated.
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
Ben Yaghlane, B., Mellouli, K.: Inference in directed evidential networks based on the transferable belief model. International Journal of Approximate Reasoning 48, 399–418 (2008)
Smets, P.: Belief Functions: the Disjunctive Rule of Combination and the Generalized Bayesian Theorem. International Journal of Approximate Reasoning 9, 1–35 (1993)
Bernard, J.M.: An introduction to the imprecise dirichlet model for multinomial data. International Journal of Approximate Reasoning 39(2-3), 123–150 (2005)
Denoeux, T.: Constructing belief functions from sample data using multinomial confidence regions. International Journal of Approximate Reasoning 42(3), 228–252 (2006)
Destercke, S.: A Decision Rule for Imprecise Probabilities Based on Pair-Wise Comparison of Expectation Bounds. In: Borgelt, C., González-Rodríguez, G., Trutschnig, W., Lubiano, M.A., Gil, M.Á., Grzegorzewski, P., Hryniewicz, O. (eds.) Combining Soft Computing and Statistical Methods in Data Analysis. AISC, vol. 77, pp. 189–197. Springer, Heidelberg (2010)
Corani, G., Zaffalon, M.: Jncc2: The java implementation of naive credal classifier 2. Journal of Machine Learning Research 9, 2695–2698 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mazigh, Y., Ben Yaghlane, B., Destercke, S. (2012). Evaluation of the Naive Evidential Classifier (NEC): A Comparison between Its Two Variants Based on a Real Agronomic Application. In: Hüllermeier, E., Link, S., Fober, T., Seeger, B. (eds) Scalable Uncertainty Management. SUM 2012. Lecture Notes in Computer Science(), vol 7520. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33362-0_51
Download citation
DOI: https://doi.org/10.1007/978-3-642-33362-0_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33361-3
Online ISBN: 978-3-642-33362-0
eBook Packages: Computer ScienceComputer Science (R0)