http://ilirias.com/jiasf/vol_13_issue_1.html

Abstract

In machine learning, distance measure plays an important role in defining the similarity between two data-items. In the paper, we discuss some of the drawbacks of distance measures (metrics) with their possibly induced clustering algorithms. Further, to overcome the drawbacks, we propose a novel intuitionistic fuzzy distance measure associated with generalized cesa´ro paranormed sequence space Cesq p(F). We also discuss some geometric properties of Cesq p(F). Moreover, the proposed distance measure is utilized in k-mean clustering algorithm to propose fuzzy c-mean clustering algorithm for Cesq p(F)