Novel Intuitionistic-Based Interval Type-2 Fuzzy Similarity Measures With Application to Clustering
- 8 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 30 (5), 1260-1271
- https://doi.org/10.1109/tfuzz.2021.3057697
Abstract
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 measures (IT-2 FSMs) as a dual concept of some semimetric distances between intuitionistic fuzzy sets (IFSs). We also prove that the extended IT-2 FSMs satisfy many common properties (i.e., reflexivity, transivity, symmetry, and overlapping). Experiments are carried out on a variety of datasets including UCI learning machine and real data. Comparative studies between the proposed IT-2 FSMs and the other well-known existing similarity measures (Gorzalczany, Bustince, Mitchell, Zeng, and Li as well as VSM and Jaccard) are performed. Obviously, the best results are obtained with the IT-2 FSMs being resilient to the high levels of uncertainty noise. We also prove that our IT-2 FSMs can overcome the drawbacks of some existing similarity measures based on the accuracy rate measure. In addition, the proposed IT-2 FSMs are joined with fuzzy C-means algorithm as a clustering method and the proposed system is compared against the existing clustering algorithms (type-1 fuzzy k-means, type-1, and type-2 fuzzy C-means, cluster forest, bagged clustering, evidence accumulation, and random projection). Relying on the clustering quality parameters R and C (equivalent to the standard classification accuracy), the advanced IT-2FSMs show higher classification accuracy of about 86% which outperforms nearly the other classifiers.Keywords
Funding Information
- Ministry of Higher Education and Scientific Research of Tunisia (LR11ES48)
This publication has 60 references indexed in Scilit:
- Similarity measures in formal concept analysisAnnals of Mathematics and Artificial Intelligence, 2011
- A comparative study of ranking methods, similarity measures and uncertainty measures for interval type-2 fuzzy setsInformation Sciences, 2009
- Switching between type-2 fuzzy sets and intuitionistic fuzzy sets: an application in medical diagnosisApplied Intelligence, 2008
- On similarity measures between intuitionistic fuzzy setsInternational Journal of Intelligent Systems, 2008
- A vector similarity measure for linguistic approximation: Interval type-2 and type-1 fuzzy setsInformation Sciences, 2008
- Similarity measures between intuitionistic fuzzy (vague) sets: A comparative analysisPattern Recognition Letters, 2007
- Pattern recognition using type-II fuzzy setsInformation Sciences, 2005
- A Hierarchical Type-2 Fuzzy Logic Control Architecture for Autonomous Mobile RobotsIEEE Transactions on Fuzzy Systems, 2004
- A note on similarity measures between vague sets and between elementsInformation Sciences, 1999
- K. Kuratowski and A. Mostowski. Set theory. English translation of XL 649(4) by M. Maczynski. PWN—Polish Scientific Publishers, Warsaw, and North-Holland Publishing Company, Amsterdam, 1968, xi + 417 pp.The Journal of Symbolic Logic, 1975