Improved Classification Approach via GEPSVM

A modified multisurface "proximal support vector machine classifier via generalized eigenvalues (GEPSVM for short)" was proposed. By defining a new principle, we designed a new classification approach via GEPSVM, namely, maximum or minimum plane distance GEPSVM (MPDGEPSVM). Unlike GEPSVM, our approach obtains two planes by solving two simple eigenvalue problems, such that it can avoid occurrence of singular problems. Our approach, compared with GEPSVM, has better classification performance. Moreover, MPDGEPSVM is over one order of magnitude faster than GEPSVM, and almost two orders of magnitude faster than SVM. Computational results on public datasets from UCI database illustrated the efficiency of MPDGEPSVM.