Cherif, Sahar and Baklouti, Nesrine and Hagras, Hani and Alimi., Adel M (2022) Novel Intuitionistic Based Interval Type-2 Fuzzy Similarity Measures with Application to Clustering. IEEE Transactions on Fuzzy Systems, 30 (5). pp. 1260-1271. DOI https://doi.org/10.1109/tfuzz.2021.3057697
Cherif, Sahar and Baklouti, Nesrine and Hagras, Hani and Alimi., Adel M (2022) Novel Intuitionistic Based Interval Type-2 Fuzzy Similarity Measures with Application to Clustering. IEEE Transactions on Fuzzy Systems, 30 (5). pp. 1260-1271. DOI https://doi.org/10.1109/tfuzz.2021.3057697
Cherif, Sahar and Baklouti, Nesrine and Hagras, Hani and Alimi., Adel M (2022) Novel Intuitionistic Based Interval Type-2 Fuzzy Similarity Measures with Application to Clustering. IEEE Transactions on Fuzzy Systems, 30 (5). pp. 1260-1271. DOI 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 paper, we first propose three new Interval Type-2 Fuzzy Similarity measures (IT-2 FSMs) as a dual concept of some semi-metric 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 cmeans 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.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Clustering; Fuzzy Distance Measure; Fuzzy Similarity Measures; Interval Type-2 Fuzzy Sets; Intuitionistic Fuzzy Sets; Noise |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 15 Mar 2021 13:34 |
Last Modified: | 30 Oct 2024 16:30 |
URI: | http://repository.essex.ac.uk/id/eprint/30023 |
Available files
Filename: 09350191.pdf
Filename: supp1-3057697.pdf