Performance of the Support Vector Machines for medical classification problems

• Autorzy: Ćwiklińska-Jurkowska M.
• Języki publikacji: EN

Abstrakty

EN

In the Support Vector Machines classification technique the best possible discriminating hyperplane between two populations is looked for by maximizing of margin between the populations' closest points. This idea is also applied for obtaining nonlinear discriminant boundaries by using different kernels for transformations, thus obtaining a nonlinear Support Vector Machines method. The nonlinear Support Vector Machines method is based on pre-processing of data to represent patterns in high dimension- usually much higher than the original variable feature space. In the presented work the dependency of Support Vector Machines performance on the kind of kernel and Support Vector Machines parameters is presented. The performance was assessed by resubstitution, 10- fold cross-validation, leave-one-out error, learning curves and Receiver Operating Characteristic curves. The kind and shape of the kernel is more important than regularization constant allowing different levels of overlapping classes. Combining boosting and Support Vector Machines did not improved performance in comparison to Support Vector Machines method alone, because both Support Vector Machines procedure and boosting are focused on observations difficult to classify.

Słowa kluczowe

EN

support vector machine; regularizing constant; kernel function; kernel parameter selection

PL

maszyna wektorów podpierających; funkcja jądra; wybór parametru jądra

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2009
• Tom: Vol. 29, no. 4
• Strony: 63--81
• Opis fizyczny: Bibliogr. 11 poz., tab., wykr.

Twórcy

autor

Ćwiklińska-Jurkowska M.

• Dept. Theoretical Backgrounds of Medical Sciences, Collegium Medicum, Nicolaus Copernicus University, ul. Jagiellońska 13, 85-067 Bydgoszcz, Poland,

Bibliografia

• 1. Cortes C. , Vapnik V.: Support-vector network. Machine Learning, 1995, 20, 1–25.
• 2. Vapnik V.N.: Statistical learning theory. Wiley, New York 1998.
• 3. Mercer J.: Functions of positive and negative type and their connection with the theory of integral equations. Philos. Trans. Royal Society London, 1909, A 209, 415–446.
• 4. Chang C.C. & Lin C.-J.: LIBSupport Vector Machine: a library for Support Vector Machines. 2001. http://www.csie.ntu.edu.tw/~cjlin/libsvm.ps.gz [Accessed 2009, Feb 1]
• 5. Hastie T., Tibshirani R. and Friedman J.: The Elements of Statistical Learning. Springer, New York 2001.
• 6. Lee Y, Lin Y, Wahba G.: Multicategory Support Vector Machines, Theory and Application to the Classification of Microarray Data and Satellite Radiance Data. Journal of American Statistical Association. 2004, 99. 67–81.
• 7. Kaufman L.: Solving the quadratic programming problem arising in Support Vector Machines; In: Advances in Kernel Methods-Support Vector Learning, eds. B. Scholkopf, C. Burges. C, Smola A., Cambridge, MA: Mit Press, 1998, 147–168.
• 8. Zhu J.T. Hastie T.: Kernel logistic regression and the import vector machines. Journal of Computational and Graphical Statistics, 2005, 14, 185–205
• 9. Bennett K.P. , Campbell C. Support vector machines: Hype or hallelujah? 2000. SIGKDD Explorations, 2(2). http://www.sigkdd.org/exploation/issue2-2/benett.pdf [Accessed 2009, Feb 1].
• 10. Skurichina M., Duin P.W.: Bagging, boosting and the RSM for linear classifiers. Pattern Analysis and Applications, 2002, 5, 121–135.
• 11. Diao L., Hu K., Lu Y., Shi C.: A method to boost Support vector Machines. Advances in Knowledge Discovery and Data Mining: 6th Pacific-Asia Conference, PAKDD 2002, Taipei, Taiwan, May 6–8, 2002. Proceedings. Editors: M.-S. Chen, P.S. Yu, B. Liu (Eds.): Springer, 2002, 463–468.