Comparison of Different Fuzzy Clustering Algorithms: A Replicated Case Study
Fuzzy clustering partitions data points of a dataset into clusters in which one data point can belong to more than one cluster. In the literature, a number of fuzzy clustering algorithms have been proposed. This paper reviews various fuzzy clustering algorithms such as Fuzzy C-Means (FCM), Possibilistic C-Means (PCM), Possibilistic Fuzzy C-Means (PFCM), Intuitionistic Fuzzy C-Means (IFCM), Kernel Fuzzy C-Means (KFCM), and Density-Oriented Fuzzy C-Means (DOFCM). We have demonstrated the experimental performance of these algorithms on some standard and synthetic datasets which include—Bensaid, Square (DUNN), D15, and D45 dataset. Then, the results are analyzed and compared to see the effectiveness of these algorithms in presence of noise and outliers.
KeywordsFuzzy clustering FCM PCM PFCM IFCM KFCM DOFCM Outliers
- 6.Sharma, S., Goel, M., Kaur, P.: Performance comparison of various robust data clustering algorithms. Int. J. Intell. Syst. Appl. 5(7), 63–71 (2013)Google Scholar
- 7.Zhang, D., Chen, S.C.: Kernel-based fuzzy and possibilistic c-means clustering. In: Proceedings of the International Conference Artificial Neural Network (2003)Google Scholar
- 13.Gosain, A., Singh, T.: DKFCM: kernelized approach to density-oriented clustering. In: Accepted in 4th International Conference on Computational Intelligence in Data Mining (ICCIDM-2017), Odisha, India, Nov 2017Google Scholar