Semi-supervised fuzzy c-medoids clustering algorithm with multiple prototype representation

Melo, Filipe M. de; Carvalho, Francisco de A. T. de

doi:10.1109/fuzz-ieee.2013.6622374

Cited by 8 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In ref. [21], a weighted fuzzy clustering model with pairwise constraints was proposed to furnish dissimilarity among the samples. However, the nonconvex optimization problems in the above models were solved by some greedy methods instead of EM type algorithm, because the convergence of EM for these problems cannot be guaranteed due to the non-convex subproblems in the maximization step.…”

Section: B Fuzzy Clustering With Pairwise Constraintsmentioning

confidence: 99%

“…For the fuzzy parameter r in fuzzy clustering, researchers suggested 1.5 ≤ γ ≤ 2.5 for its better performance with the suitable fuzzy level [6], [22], [18], [21], [14], [40], [37], [19], [20]. Thus, we set γ = 2 in the main problem (5) for its computational simplicity.…”

Section: Solving the Main Problemmentioning

confidence: 99%

“…An simple external information is the pairwise constraints [15], [16], which assign several pairs of samples in either a cluster or two different clusters, called must-link or cannot-link respectively. In the literature, there have been many clustering and fuzzy clustering models guided by pairwise constraints [15], [16], [17], [18], [19], [20], [21], [22]. The images are derived from the JAFFE database [23], and this database also provides a labeled fuzzy expressions (i.e., the ground truth).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fuzzy Discriminant Clustering with Fuzzy Pairwise Constraints

Wang,

Bai

et al. 2021

Preprint

View full text Add to dashboard Cite

In semi-supervised fuzzy clustering, this paper extends the traditional pairwise constraint (i.e., must-link or cannot-link) to fuzzy pairwise constraint. The fuzzy pairwise constraint allows a supervisor to provide the grade of similarity or dissimilarity between the implicit fuzzy vectors of a pair of samples. This constraint can present more complicated relationship between the pair of samples and avoid eliminating the fuzzy characteristics. We propose a fuzzy discriminant clustering model (FDC) to fuse the fuzzy pairwise constraints. The nonconvex optimization problem in our FDC is solved by a modified expectation-maximization algorithm, involving to solve several indefinite quadratic programming problems (IQPPs). Further, a diagonal block coordinate decent (DBCD) algorithm is proposed for these IQPPs, whose stationary points are guaranteed, and the global solutions can be obtained under certain conditions. To suit for different applications, the FDC is extended into various metric spaces, e.g., the Reproducing Kernel Hilbert Space. Experimental results on several benchmark datasets and facial expression database demonstrate the outperformance of our FDC compared with some state-of-the-art clustering models.

show abstract

Section: B Fuzzy Clustering With Pairwise Constraintsmentioning

confidence: 99%