Discriminant analysis via support vectors
Neurocomputing, pp. 1669-1675, 2010.
EI WOS SCOPUS
In this paper, we show how support vector machine (SVM) can be employed as a powerful tool for k-nearest neighbor (kNN) classifier. A novel multi-class dimensionality reduction approach, discriminant analysis via support vectors (SVDA), is proposed. First, the SVM is employed to compute an optimal direction to discriminant each two classe...More
Full Text (Upload PDF)
PPT (Upload PPT)