A New Approach That Selects a Single Hyperplane from the Optimal Pairwise Linear Classifier

摘要

In this paper, we introduce a new approach to selecting the best hyper-plane classifier (BHC) from the optimal pairwise linear classifier is given. We first propose a procedure for selecting the BHC, and analyze the conditions in which the BHC is selected. In one of the cases, it is formally shown that the BHC and Fisher's classifier (FC) are coincident. The empirical and graphical analysis on synthetic data and real-life datasets from the UCI machine learning repository, which involves the optimal quadratic classifier, the BHC, the optimal pairwise linear classifier, and FC.