A novel semisupervised classification method via membership and polyhedral conic functions

Abstract

In real-world problems, finding sufficient labeled data for defining classification rules is very difficult. Thispaper suggests a new semisupervised multiclass classification method. In the initialization, new membership functionsare defined by utilizing the labeled data’s medoids and means. Then the unlabeled points are labeled with the class ofthe highest membership value. In the supervised learning phase, separation via the polyhedral conic functions (PCFs)approach is improved by using defined membership values in the linear programming problem. The suggested algorithmis tested on real-world datasets and compared with the state-of-the-art semisupervised methods. The results obtainedindicate that the suggested algorithm is effective in classification and is worth studying.