Abstract
In this paper, we apply support vector machine (SVM) to knowledge discovery (KD) and confirm its effectiveness with a benchmark data set. SVM has been successfully applied to problems in various domains. However, its effectiveness as a KD method is unknown. We propose SVM for KD, which deals with a classification problem with a binary class, by rescaling each attribute based on z-scores. SVM for KD can sort attributes with respect to their effectiveness in discriminating classes. Moreover, SVM for KD can discover crucial examples for discrimination. We settled six discovery tasks with the meningoencephalitis data set, which is a benchmark data set in KD. A domain expert ranked the discovery outcomes of SVM for KD from one to five with respect to several criteria. Selected attributes in six tasks are all valid and useful: their average scores are 3.8-4.0. Discovering order of attributes about usefulness represents a challenging problem. However, concerning this problem, our method achieved a score of more than or equal to 4.0 in three tasks. Besides, crucial examples for discrimination and typical examples for each class agree with medical knowledge. These promising results demonstrate the effectiveness of our approach.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Cortes, C., Vapnik, V.: Support Vector Network. Machine Learning 20(3), 1–25 (1995)
Joachims, T.: Text Categorization with Support Vector Machines: Learning with Many Relevant Features. In: Proc. Tenth European Conf. Machine Learning (ECML), pp. 137–142 (1998)
Kaufman, L., Rousseeuw, P.: Finding Groups in Data. John Wiley & Sons, Chichester (1990)
Knorr, E.M., Ng, R.T.: Algorithms for Mining Distance-Based Outliers in Large Datasets. In: Proc. 24th Ann. Int’l Conf. Very Large Data Bases (VLDB), pp. 392–403 (1998)
Osuna, E., Freund, R., Girosi, F.: Training Support Vector Machines: an Application to Face Detection. In: Kaufman, L., Rousseeuw, P. (eds.) Proc. Computer Vision and Pattern Recognition, pp. 130–136 (1997)
Pontil, M., Verri, A.: Support Vector Machines for 3D Object Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 20(6), 637–646 (1998)
Suzuki, E.: Autonomous Discovery of Reliable Exception Rules. In: Proc. Third Int’l Conf. Knowledge Discovery and Data Mining (KDD), pp. 259–262 (1997)
Tsumoto, S., et al.: Comparison of Data Mining Methods using Common Medical Datasets. In: ISM Symp.: Data Mining and Knowledge Discovery in Data Science, pp. 63–72 (1999)
Tsumoto, S.: Knowledge Discovery in Clinical Databases: an Experiment with Rule Induction and Statistics. In: Raś, Z.W., Skowron, A. (eds.) ISMIS 1999. LNCS (LNAI), vol. 1609, pp. 349–357. Springer, Heidelberg (1999)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sugaya, S., Suzuki, E., Tsumoto, S. (1999). Support Vector Machines for Knowledge Discovery. In: Żytkow, J.M., Rauch, J. (eds) Principles of Data Mining and Knowledge Discovery. PKDD 1999. Lecture Notes in Computer Science(), vol 1704. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-48247-5_74
Download citation
DOI: https://doi.org/10.1007/978-3-540-48247-5_74
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66490-1
Online ISBN: 978-3-540-48247-5
eBook Packages: Springer Book Archive