Data mining is a collection of exploration methods based on advanced analytical tools and techniques for handling huge amount of information. Clustering is a useful technique for discovery of knowledge from a dataset. Distance measure plays an important role in clustering. It is used to measure the similarity or dissimilarity between two data points. Euclidean distance measure is normally used in most clustering methods. Some of the limitations of this measure are inability to handle noise and outlier data points, not suitable for sparse data and clusters with only elliptical shapes. In this paper, fuzzy clustering is proposed using different similarity measures such as non-negative vector similarity coefficient (NVSC), Correlation and Cosine. The performance of the algorithm is compared with various similarity measures using five real life benchmark sets including Wine, Liver Disorders, Pima Indian Diabetes, Haberman’s Survival and Statlog (Heart). Experimental results show that fuzzy clustering based on Cosine similarity measure achieves minimum fitness value, minimum intra-cluster distance and maximum inter-cluster distance on various data sets than other similarity measures.

Fuzzy Clustering, Similarity Measures, Cluster Validity

[1] J. Han and M. Kamber, “Data mining: Concepts and Techniques”, Morgan Kaufmann, San Francisco, 2001.
[2] P. Berkhin, “Survey clustering Data Mining Techniques”, Technical Report, Accrue Software, San Jose, California, 2002.
[3] J. MacQueen, “Some Methods for Classification and Analysis of Multivariate Observations”, Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1, pp. 281-297, 1967.
[4] J.C. Dunn, “A fuzzy relative of the ISODATA process and its use in detecting compact well separated clusters”, Journal of Cybernetics, Vol. 3, pp. 32-57, 1973.
[5] J.C. Bezdek, “Pattern Recognition with Fuzzy Objective Function Algorithms”, Plenum Press, New York, 1981.
[6] J. Dong and M. Qi, “A new clustering algorithm based on PSO with the jumping mechanism”, Proceedings of the IEEE third international symposium on intelligent information technology applications, 2009.
[7] Soumi Ghose and Sanjay Kumar Dubey, “Comparative Analysis of K-Means and Fuzzy C-Means Algorithms”, International Journal of Advanced Computer Science and Applications (IJACSA), Vol. 4, No. 4, pp. 35-39, 2013.
[8] Archana Singh, Avantika Yadav and Ajay Rana, “K-means with Three Different Distance Metrics”, International Journal of Computer Applications, Vol. 67, No. 10, pp. 13-17, 2013.
[9] Hadi Nasooti, Marzieh Ahmadzadeh, Manjeh Kesht Gary and S. Vahid Farrahi, “The impact of Distance Metrics on K-means Clustering Algorithm Using in Network Intrusion Detection Data”, International Journal of Computer Networks and Communications Security, Vol. 3, No. 5, pp. 225-228, 2015.
[10] Jasmine Irani, Nitin Pise and Madhura Phatak, “Clustering Techniques and the Similarity Measures used in Clustering: A Survey”, International Journal of Computer Applications, Vol. 134, No. 7, pp. 9-14, 2016.
[11] Ms. Kothariya Arzoo and Kirit Rathod, “K-Means Algorithm with different distance metrics in spatial data mining with uses of NetBeans IDE 8.2”, International Research Journal of Engineering and Technology (IRJET), Vol. 4, Issue 4, pp. 2363-2368, 2017.
[12] V.P. Mahatme and Dr. K.K. Bhoyar, “Impact of Distance Metrics on the Performance of K-Means and Fuzzy C-means Clustering – An Approach to access Student’s Performance in E-Learning Environment”, International Journal of Advanced Research in Computer Science, Vol. 9, No. 1, pp. 887-892, 2018.
[13] Weina Wang and Yunije Zhang, “On Fuzzy Cluster Validity Indices”, Fuzzy Sets and Systems, Vol. 158, Issue 19, pp. 2095-2117, 2007.