A Type-2 Fuzzy Concepts Lexicalized Representation by Perceptual Reasoning and Linguistic Weighted Average: A Comparative Study

Cherif, Sahar; Baklouti, Nesrine; Alimi, Adel M.; Snášel, Václav

doi:10.1007/978-3-319-27221-4_7

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to obtain Type-2 membership functions, the Enhanced Interval approach (EIA) [53]- [55], which is a generalization of the Interval Approach (IA) introduced by [56], was applied to model imprecision. The main advantage of the EIA is that it results in thinner and narrower Footprint Of Uncertainty (FOU) than the IA algorithm [57]. The EIA consists mainly in transforming words into IT-2 FSs and generating FOUs for all data attributes.…”

Section: Performance Analysis a Adopted Approachmentioning

confidence: 99%

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

Cherif¹,

Baklouti

Hagras

et al. 2022

IEEE Trans. Fuzzy Syst.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Performance Analysis a Adopted Approachmentioning

confidence: 99%