Fast training of support vector machines using sequential minimal optimization
Advances in kernel methods
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Constructing Boosting Algorithms from SVMs: An Application to One-Class Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimating the Support of a High-Dimensional Distribution
Neural Computation
Improvements to Platt's SMO Algorithm for SVM Classifier Design
Neural Computation
A comparison of methods for multiclass support vector machines
IEEE Transactions on Neural Networks
Coincidence of the solutions of the modified problem with the original problem of v-MC-SVM
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
| Hi-index | 0.00 |
A new model of multi-class support vector machine with parameter v (v-MC-SVM) is proposed firstly based on v- SVM. Existence of optimal solutions and dual problem of v-MC-SVM are also given. Because the constraints of v- MC-SVM are too complicated, one-class SVM problem is given by adding bm to the objective function of v-MC-SVM and employing the Kesler's construction which simplify the original problem. The optimal solutions of one-class SVM problem are unchanged when its constraint eTα≥v is replaced with eTα = v. Numerical testing results show that the speed of v-MC-SVM algorithm is faster than that of QPMC-SVM algorithm under the same accuracy rate.