A novel intuitionistic fuzzy similarity measure with applications in decision-making, pattern recognition, and clustering problems

The distance and similarity measures are two interrelated information measures that can be effectively used to quantify the degree of deviation and degree of similarity between the pairs of objects. Among several interesting measures on intuitionistic fuzzy sets, the similarity measure is a fundamental and prominent tool for handling the imperfect and ambiguous information. The researchers have suggested several similarity measures, but some of them produce conflicting results in practical significance and violate the basic axioms of similarity. In this communication, we propose a novel similarity measure and visualize it, we also discuss the axioms of similarity and non-linearity property from graphical perspective. The characteristics of the suggested measure are demonstrated with the help of various numerical experiments and it is analyzed that the developed measure can overcome the unreasonable cases of the existing measures. We also discuss the effectiveness of the suggested measure over various existing measures in context of linguistic hedges. An algorithm for pattern recognition based on the proposed measure is developed and demonstrated with numerical experiments that stated measure suppresses the limitations of prevailing measures. Further, the efficiency of the suggested measure is examined in clustering analysis by matching the objects on the different confidence levels. Finally, a new decision-making algorithm based on the suggested measure is developed and a comparative study with existing approach is performed to establish its validity.