- Title
- Finding compact and well-separated clusters : clustering using silhouette coefficients
- Creator
- Bagirov, Adil; Aliguliyev, Ramiz; Sultanova, Nargiz
- Date
- 2023
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/190442
- Identifier
- vital:17617
- Identifier
-
https://doi.org/10.1016/j.patcog.2022.109144
- Identifier
- ISSN:0031-3203 (ISSN)
- Abstract
- Finding compact and well-separated clusters in data sets is a challenging task. Most clustering algorithms try to minimize certain clustering objective functions. These functions usually reflect the intra-cluster similarity and inter-cluster dissimilarity. However, the use of such functions alone may not lead to the finding of well-separated and, in some cases, compact clusters. Therefore additional measures, called cluster validity indices, are used to estimate the true number of well-separated and compact clusters. Some of these indices are well-suited to be included into the optimization model of the clustering problem. Silhouette coefficients are among such indices. In this paper, a new optimization model of the clustering problem is developed where the clustering function is used as an objective and silhouette coefficients are used to formulate constraints. Then an algorithm, called CLUSCO (CLustering Using Silhouette COefficients), is designed to construct clusters incrementally. Three schemes are discussed to reduce the computational complexity of the algorithm. Its performance is evaluated using fourteen real-world data sets and compared with that of three state-of-the-art clustering algorithms. Results show that the CLUSCO is able to compute compact clusters which are significantly better separable in comparison with those obtained by other algorithms. © 2022 Elsevier Ltd
- Publisher
- Elsevier Ltd
- Relation
- Pattern Recognition Vol. 135, no. (2023), p.; http://purl.org/au-research/grants/arc/DP190100580
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © 2022 Elsevier Ltd
- Subject
- 4603 Computer vision and multimedia computation; 4605 Data management and data science; 4611 Machine learning; Cluster analysis; Cluster validity index; Incremental algorithm; Nonsmooth optimization; Silhouette coefficients
- Reviewed
- Hits: 389
- Visitors: 373
- Downloads: 0