Maximum margin classification based on flexible convex hulls
作者： Ming Zeng , Yu Yang , Jinde Zheng , Junsheng Cheng
DOI: 10.1016/J.NEUCOM.2014.07.038
关键词: Convex hull 、 Convex polytope 、 Combinatorics 、 Proper convex function 、 Orthogonal convex hull 、 Convex analysis 、 Convex set 、 Mathematical optimization 、 Convex optimization 、 Mathematics 、 Convex combination
摘要: Based on defining a flexible convex hull, maximum margin classification based hulls (MMC-FCH) is presented in this work. The hull defined our work class region approximation looser than but tighter an affine hull. MMC-FCH approximates each with of its training samples, and then finds linear separating hyperplane that maximizes the between by solving closest pair points problem. method can be extended to nonlinear case using kernel trick, multi-class problems are dealt constructing binary pairwise classifiers as support vector machine (SVM). experiments several databases show proposed compares favorably (MMC-CH) or (MMC-AH). A for approximation.Maximum work.MMC-FCH hull.MMC-FCH optimal
elsevier.com
sci-hub.se 参考文章(28)
S. Knerr, L. Personnaz, G. Dreyfus, Single-layer learning revisited: a stepwise procedure for building and training a neural network NATO Neurocomputing. pp. 41- 50 ,(1990) , 10.1007/978-3-642-76153-9_5
Shiliang Sun, You Ji, Yue Lu, Multitask multiclass privileged information support vector machines international conference on pattern recognition. pp. 2323- 2326 ,(2012)
Erin J. Bredensteiner, Kristin P. Bennett, Duality and Geometry in SVM Classifiers international conference on machine learning. pp. 57- 64 ,(2000)
David M.J. Tax, Robert P.W. Duin, Support Vector Data Description Machine Learning. ,vol. 54, pp. 45- 66 ,(2004) , 10.1023/B:MACH.0000008084.60811.49
Jian-xiong Dong, Adam Krzyżak, Ching Y. Suen, An improved handwritten Chinese character recognition system using support vector machine artificial neural networks in pattern recognition. ,vol. 26, pp. 1849- 1856 ,(2005) , 10.1016/J.PATREC.2005.03.006
M Arun Kumar, Madan Gopal, None, A comparison study on multiple binary-class SVM methods for unilabel text categorization Pattern Recognition Letters. ,vol. 31, pp. 1437- 1444 ,(2010) , 10.1016/J.PATREC.2010.02.015
Zheng Wang, Shuicheng Yan, Changshui Zhang, Active learning with adaptive regularization Pattern Recognition. ,vol. 44, pp. 2375- 2383 ,(2011) , 10.1016/J.PATCOG.2011.03.008
Hakan Cevikalp, Bill Triggs, Hasan Serhan Yavuz, Yalçın Küçük, Mahide Küçük, Atalay Barkana, Large margin classifiers based on affine hulls Neurocomputing. ,vol. 73, pp. 3160- 3168 ,(2010) , 10.1016/J.NEUCOM.2010.06.018
S. Abbasion, A. Rafsanjani, A. Farshidianfar, N. Irani, Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine Mechanical Systems and Signal Processing. ,vol. 21, pp. 2933- 2945 ,(2007) , 10.1016/J.YMSSP.2007.02.003
Yu Yang, Dejie Yu, Junsheng Cheng, None, A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM Measurement. ,vol. 40, pp. 943- 950 ,(2007) , 10.1016/J.MEASUREMENT.2006.10.010