Novel Intuitionistic-Based Interval Type-2 Fuzzy Similarity Measures With Application to Clustering

Similarity measures have been widely used in applications dealing with reasoning, classification, and information retrieval. In this article, we first propose three new interval type-2 fuzzy similarity (IT-2 FSMs) as a dual concept of some semimetric distances between intuitionistic sets (IFSs). We also prove that the extended IT-2 FSMs satisfy many common properties (i.e., reflexivity, transivity, symmetry, overlapping). Experiments are carried out on variety datasets including UCI learning machine real data. Comparative studies proposed other well-known existing (Gorzalczany, Bustince, Mitchell, Zeng, Li well VSM Jaccard) performed. Obviously, best results obtained being resilient to high levels uncertainty noise. our can overcome drawbacks based accuracy rate measure. addition, joined C-means algorithm clustering method system is compared against algorithms (type-1 k-means, type-1, C-means, cluster forest, bagged clustering, evidence accumulation, random projection). Relying quality parameters R C (equivalent standard classification accuracy), advanced IT-2FSMs show higher about 86% which outperforms nearly classifiers.