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. This paper suggests a new semisupervised multiclass classification method. In the initialization, new membership functions are defined by utilizing the labeled data's medoids and means. Then the unlabeled points are labeled with the class of the 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 algorithm is tested on real-world datasets and compared with the state-of-the-art semisupervised methods. The results obtained indicate that the suggested algorithm is effective in classification and is worth studying.

A Novel Membership Function Definition for Fuzzy Classification

“…From this point of view, the automatic construction of membership functions is preferable. Various methods based on machine learning and statistics are proposed in the literature to generate membership functions (Mendes et al, 2001;Sanz et al, 2010;Makrehchi & Kamel, 2011;Borkar & Rajeswari, 2013;Jamsandekar & Mudholkar, 2014;Bhattacharyya & Mukherjee, 2020;Rapheal & Bhattacharya, 2020;Satı, 2020;Xie et al, 2021;Azam et al, 2021). Xie et al (2021) proposed a novel polynomial membership function approach for polynomial fuzzy system stability analysis.…”

“…In the paper of Satı (2020), by using the labeled data's means and medoids novel membership functions were defined for labeling unsupervised ones and also defined membership values were used in the classification phase in the linear programming problem. The suggested algorithm was tested on real-world datasets and compared with the state-of-the-art semi-supervised methods.…”