Feature selection for the SVM: An application to hypertension diagnosis
作者： Chao-Ton Su , Chien-Hsin Yang
DOI: 10.1016/J.ESWA.2006.10.010
关键词: Polynomial kernel 、 Artificial neural network 、 Statistical learning theory 、 Machine learning 、 Support vector machine 、 Backpropagation 、 Kernel method 、 Kernel (linear algebra) 、 Kernel (statistics) 、 Least squares support vector machine 、 Feature selection 、 Radial basis function kernel 、 Artificial intelligence 、 Computer science 、 Pattern recognition
摘要: A support vector machine (SVM) is a novel classifier based on the statistical learning theory. To increase performance of classification, approach SVM with kernel usually used in classification tasks. In this study, we first attempted to investigate kernel. Several functions, polynomial, RBF, summation, and multiplication were employed feature selection developed [Hermes, L., & Buhmann, J. M. (2000). Feature for machines. Proceedings international conference pattern recognition (ICPR'00) (Vol. 2, pp. 716-719)] was utilized determine important features. Then, hypertension diagnosis case implemented 13 anthropometrical factors related selected. Implementation results show that combined better than single approach. Compared backpropagation neural network method, method found have two epidemiological indices such as sensitivity specificity.
nctu.edu.tw
acm.org
elsevier.com参考文章(42)
Ryan Rifkin, Sayan Mukherjee, Support Vector Machine Classification of Microarray Data ,(2001)
Chao-Ton Su, Hyh-Hwa Hsu, Chih-Hung Tsai, Knowledge mining from trained neural networks Journal of Computer Information Systems. ,vol. 42, pp. 61- 70 ,(2002)
B Schölkopf, Support vector learning Oldenbourg München, Germany. ,(1997)
Bernhard Schölkopf, Alexander J. Smola, Learning with Kernels The MIT Press. pp. 626- ,(2018) , 10.7551/MITPRESS/4175.001.0001
Barbara Hammer, Kai Gersmann, A Note on the Universal Approximation Capability of Support Vector Machines Neural Processing Letters. ,vol. 17, pp. 43- 53 ,(2003) , 10.1023/A:1022936519097
Hiroshi Motoda, Huan Liu, Feature Selection for Knowledge Discovery and Data Mining ,(1998)
M.-L. Wang, W.-J. Li, W.-B. Xu, Support vector machines for prediction of peptidyl prolyl cis/trans isomerization Journal of Peptide Research. ,vol. 63, pp. 23- 28 ,(2008) , 10.1046/J.1399-3011.2004.00100.X
N. Aronszajn, Theory of Reproducing Kernels. Transactions of the American Mathematical Society. ,vol. 68, pp. 337- 404 ,(1950) , 10.1090/S0002-9947-1950-0051437-7
L. Mykkanen, S. M. Haffner, T. Ronnemaa, R. N. Bergman, M. Laakso, Low Insulin Sensitivity is Associated with Clustering of Cardiovascular Disease Risk Factors American Journal of Epidemiology. ,vol. 146, pp. 315- 321 ,(1997) , 10.1093/OXFORDJOURNALS.AJE.A009272
Bing Dong, Cheng Cao, Siew Eang Lee, Applying support vector machines to predict building energy consumption in tropical region Energy and Buildings. ,vol. 37, pp. 545- 553 ,(2005) , 10.1016/J.ENBUILD.2004.09.009