Analysis of the margin setting algorithm as a margin-based spherical classification method

Spherical classification uses hypersphere as decision boundary. Margin setting is a new learning algorithm for spherical classification. In this paper, an analysis of margin setting is presented using probabilities of miss classification (MC) and over classification (OC). Experiments were carried out using Monte Carlo method. The result showed that margin setting is a margin-based classifier whose performance tends to improve with an increased margin within a certain range. Besides, the multi-sphere strategy employed by the margin setting algorithm allows it to achieve lower probabilities of MC, OC and non-classification than classifiers using a single sphere as its decision boundary.