Abstract
Support vector machine (SVM) and support vector data description (SVDD) are the well-known kernel-based methods for pattern classification. SVM constructs an optimal hyperplane whereas SVDD constructs an optimal hypersphere to separate data between two classes. SVM and SVDD have been compared in pattern classification experiments, however there is no theoretical work on comparison of these methods. This paper presents a new theoretical model to unify SVM and SVDD. The proposed model constructs two optimal points which can be transformed to hyperplane or hypersphere. Therefore SVM and SVDD are regarded as special cases of this proposed model. We applied the proposed model to analyse the dataset III for motor imagery problem in BCI Competition II and achieved promising results.
Original language | English |
---|---|
Title of host publication | International Conference on Neural Information Processing (ICONIP 2011) |
Subtitle of host publication | Lecture Notes in Computer Science |
Editors | Bao-Liang Lu, Liqing Zhang, James Kwok |
Place of Publication | Germany |
Publisher | Springer |
Pages | 692-700 |
Number of pages | 9 |
Volume | 7062 |
ISBN (Electronic) | 9783642249556 |
ISBN (Print) | 9783642249549 |
DOIs | |
Publication status | Published - 2011 |
Event | 18th International Conference on Neural Information Processing - Shanghai, Shanghai, China Duration: 13 Nov 2011 → 17 Nov 2011 |
Conference
Conference | 18th International Conference on Neural Information Processing |
---|---|
Country/Territory | China |
City | Shanghai |
Period | 13/11/11 → 17/11/11 |