In this paper, we propose a least squares support vector machine with parametric margin (Par-LSSVM) for binary classification, which only needs to solve a system of linear equation. Par-LSSVM is able to handle the datasets with heteroscedastic noise. And the closer hyperplane to the test data point gives the class label, and this makes Par-LSSVM capable of dealing with “Cross Planes” datasets. The experimental results on several artificial, benchmark and USPS datasets indicate that our proposed algorithm outperforms Par-ν-SVM for binary classification problem.
CortesC. and VapnikV., Support-vector networks, Machine Learning20(3) (1995), 273–297.
2.
DengN., TianY. and ZhangC., Support vector machines: Optimization based theory, algorithms, and extensions(Vol, 29). CRC Press, 2012.
3.
VapnikV., The Nature of Statistical Learning Theory, Springer-Verlag, 1995.
4.
SuykensJ.A. and VandewalleJ., Least squares support vector machine classifiers, Neural Processing Letters9(3) (1999), 293–300.
5.
HaoP.Y., New support vector algorithms with parametric insensitive/margin model, Neural Networks23(1) (2010), 60–73.
6.
ChangC.C. and LinC.J., Training v-support vector classifiers: Theory and algorithms, Neural Computation13(9) (2001), 2119–2147.
7.
MangasarianO.L. and WildE.W., Multisurface proximal support vector machine classification via generalized eigenvalues, Pattern Analysis and Machine Intelligence, IEEE Transactions on28(1) (2006), 69–74.
8.
JayadevaKhemchandani R. and
ChandraS., Twin support vector machines for pattern classification, Pattern Analysis and Machine Intelligence, IEEE Transactions on29(5) (2007), 905–910.
9.
ShaoY.H., ChenW.J. and DengN.Y., Nonparallel hyperplane support vector machine for binary classification problems, Information Sciences263 (2014), 22–35.
