Incorporating Fuzziness to CLARANS
In this paper we propose a way of handling fuzziness while mining large data. Clustering Large Applications based on RANdomized Search (CLARANS) is enhanced to incorporate the fuzzy component. A new scalable approximation to the maximum number of neighbours, explored at a node, is developed. The goodness of the generated clusters is evaluated in terms of validity indices. Experimental results on various data sets is run to converge to the optimal number of partitions.
KeywordsData mining CLARANS medoid fuzzy sets clustering
- 1.Kaufman, L., Rousseeuw, P.J.: Finding Groups in Data: An Introduction to Cluster Analysis. John Wiley & Sons, New York (1990)Google Scholar
- 3.Mitra, S., Acharya, T.: Data Mining: Multimedia, Soft Computing, and Bioinformatics. John Wiley, New York (2003)Google Scholar
- 5.Fuzzy logic, neural networks, and soft computing. Communications of the ACM 37, 77–84 (1994)Google Scholar