New fuzzy similarity measures: From intuitionistic to type-2 fuzzy sets

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

doi:10.1109/fuzz-ieee.2017.8015696

Cited by 6 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various similarity measures e.g. Jaccard defined in [37], S1, S2, proposed in [38] measures are applied between interval type-2 fuzzy sets to define the similarity score. In this section, we briefly present expressions of these similarity measures between type-2 fuzzy sets.…”

Section: Interval Type-2 Fuzzy Similarity Measure It2fsmmentioning

confidence: 99%

“…A Jaccard Similarity measure [37] between two IT-2 FSs denoted as IT2FSMj (A, B) is presented as follows: [38] have generated new IT2FSM as an extension of the Baccour's distance proposed in [44] and named as IT2FSM1 and IT2FSM2.…”

Section: Interval Type-2 Fuzzy Similarity Measure It2fsmmentioning

confidence: 99%

“…Subsequently, based on the verified properties, IT2FSM1 and IT2FSM2 are Fuzzy Similarity Measures. Fuzzy Similarity Measure Properties: Definition: The properties of a fuzzy similarity measure between three sets A, B and C of F S(X) are proposed in [38], [37], [44], as follows: • P4. Overlapping: If A ∩ B = ∅ then S(A, B) > 0 otherwise S(A, B) = 0 A similarity value can vary from -1 to 1.…”

Section: Interval Type-2 Fuzzy Similarity Measure It2fsmmentioning

confidence: 99%

“…A comparative study between type 1 and type 2 FSM can be found in [37]. Three new Interval Type-2 Fuzzy Similarity measures (IT-2 FSMs) between Intuitionistic Fuzzy Sets were exposed by Cherif et al in [38]. In this paper, we propose a new Interval Type-2 Beta Fuzzy Near sets approach to Content based Image Retrieval.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Interval Type-2 Beta Fuzzy Near Sets Approach to Content-Based Image Retrieval

Ghozzi

Baklouti

Hagras

et al. 2022

IEEE Trans. Fuzzy Syst.

Self Cite

View full text Add to dashboard Cite

In computer-based search systems, similarity plays a key role in replicating the human search process which underlies many natural abilities, such as image recovery, language comprehension, decision making, or pattern recognition. The search for images consists in establishing a correspondence between the available images and those sought by the user, by measuring the similarity between the images. In fact, image search per content is generally based on the similarity between the visual characteristics of the images. The distance function used to evaluate the similarity between images depends notonly on the criteria of the search but also on the representation of the characteristics of the image. This is the main idea of a contentbased image retrieval (CBIR) system. In this article, we first constructed type-2 beta fuzzy membership of descriptor vectors to help manage inaccuracy and uncertainty of the characteristics extracted from the feature of images. Subsequently, the retrieved images are ranked according to the novel similarity measure, which is noted type-2 fuzzy nearness measure (IT2FNM). By analogy to Type-2 Fuzzy Logic, and motivated by a near sets theory, we advanced a new fuzzy similarity measure (FSM) noted as interval type-2 fuzzy nearness measure (IT-2 FNM). Then, we proposed three new IT-2 FSMs and provided mathematical justification to demonstrate that the proposed FSMs satisfy proximity properties (i.e. reflexivity, transitivity, symmetry, and overlapping). The experimental results generated using three image databases show consistent and significant results.

show abstract

Section: Interval Type-2 Fuzzy Similarity Measure It2fsmmentioning

confidence: 99%

Section: Interval Type-2 Fuzzy Similarity Measure It2fsmmentioning

confidence: 99%

Section: Interval Type-2 Fuzzy Similarity Measure It2fsmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Interval Type-2 Beta Fuzzy Near Sets Approach to Content-Based Image Retrieval

Ghozzi

Baklouti

Hagras

et al. 2022

IEEE Trans. Fuzzy Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…A comparison of reflexivity, symmetry, transivity and overlapping properties between the above-described Type-2 FSMs is summarized in Table I. [46]. The main idea is to extend Baccour's semi-metric distance measures [10] for Intuitionistic Fuzzy Sets (see equations 7, 8 and 10).…”

Section: B Interval Type-2 Fuzzy Similarity Measuresmentioning

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