A Study on the Linguistic Explanation of Online Classification Mechanism Using Confidence-Weighted Learning Fuzzy Classifiers

Abstract

Fuzzy classifiers can linguistically explain its mechanism while achieving high classification accuracy. In this paper, we aim to explain the classification mechanism in dynamic environments where the classification boundary changes over time. For this purpose, we propose an online updating of fuzzy classifiers by means of Confidence-Weighted Learning. We have confirmed that the model can linguistically explain the classification mechanism in dynamic environments by examining how the weights of the fuzzy If-Then rules change.