Linguistic Representation by Fuzzy Formal Concept and Interval Type-2 Feature Selection

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

doi:10.1007/978-3-319-53480-0_105

Cited by 1 publication

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some real world applications, data optimization, feature selection [15], [16], classification and similarity factorization [17], [18] are based essentially on the definition of adequate measures. In this context, several types of measures such as distance [4], entropy [19], correlation [20], divergence [21], dissimilarity [22] and similarity measures [10] were introduced in the literature.…”

Section: Introductionmentioning

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