Abstract
Fuzzy C-means (FCM) clustering algorithm is commonly used in data mining tasks. It has the advantage of producing good modeling results in many cases. However, it is sensitive to outliers and the initial cluster centers. In addition, it could not get the accurate cluster number during the algorithm. To overcome the above problems, a novel FCM algorithm based on gravity and cluster merging was presented in this paper. By using gravity in this algorithm, the influence of outliers was minimized and the initial cluster centers were selected. And by using cluster merging, an appropriate number of clustering could be specified. The experimental evaluation shows that the modified method can effectively improve the clustering performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dunn, J.C.: A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters. Journal of Cybernetics 3, 32–57 (1973)
Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press, New York (1981)
Davé, R.N.: Characterization and detection of noise in clustering. Pattern Recognition Letters 12, 657–664 (1991)
Frigui, H., Krishnapuram, R.: Clustering by competitive agglomeration. Pattern Recognition 30, 1109–1119 (1997)
Sun, H.J., Wang, S.R., Jiang, Q.H.: FCM-Based Model Selection Algorithms for Determining the Number of Clusters. Pattern Recognition 37, 2027–2037 (2004)
Indulska, M., Orlowska, M.E.: Gravity Based Spatial Clustering. In: Proceedings of the 10th ACM International Symposium on Advances in Geographic Information Systems, pp. 125–130. Year of Publication, Virginia (2002)
Frossyniotis, D., Pertselakis, M., Stafylopatis, A.: A Multi-Clustering Fusion Algorithm. In: Proceedings of the Second Hellenic Conference on Artificial intelligence, pp. 225–236. Year of Publication, Thessaloniki (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhong, J., Liu, L., Li, Z. (2010). A Novel Clustering Algorithm Based on Gravity and Cluster Merging. In: Cao, L., Feng, Y., Zhong, J. (eds) Advanced Data Mining and Applications. ADMA 2010. Lecture Notes in Computer Science(), vol 6440. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17316-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-17316-5_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17315-8
Online ISBN: 978-3-642-17316-5
eBook Packages: Computer ScienceComputer Science (R0)