Abstract
The MSRD (Most Similar Relation Diagram) of a dataset is a weighted undirected graph constructed from an initial dataset. In the MSRD, each datum represented by a vertex, is connected with its MSD (Most Similar Data), and each MSRG (Most Similar Relation Group), represented by a sub-graph, is connected with its MSG (most similar group)through connecting the most similar pairs of data between the two sub-graph. The clustering algorithm based on the MSRD involves two stages: constructing the MSRD of the dataset and cutting the diagram into sub-graphs (clusters). In this paper, we developed a package of methods for the later stage and applied them to some synthesized and real datasets. The performance verified the validity of these methods and demonstrated that the MSRD based clustering is a universal and rich algorithm.
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
Jain, A.K.: Data clustering: 50 years beyond K-means. Pattern Recognition Letters 31, 651–666 (2010)
Fred, A., Jain, A.K.: Data clustering using evidence accumulation. In: Proc. Internat. Conf. Pattern Recognition, ICPR (2002)
Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-Supervised Learning. MIT Press, Cambridge (2006)
Bekkerman, R., El-Yaniv, R., McCallum, A.: Multi-way distributional clustering via pairwise interactions. In: Proc. 22nd Internat. Conf. Machine Learning, pp. 41–48 (2005)
Filippone, M., Camastrab, F., Masulli, F., Rovetta, S.: A survey of kernel and spectral methods for clustering. Pattern Recognition 41, 176–190 (2008)
Yu, Y., Bai, Y.S., Xu., W.H., et al.: A Clustering Method Based on the Most Similar Relation Diagram of Datasets. In: 2010 IEEE International Conference on Granular Computing, San Jose, California, August 14-16, pp. 598–603 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, W.H., Zhu, M., Jiang, Y.R., Bai, Y.S., Yu, Y. (2011). The Clustering Algorithm Based on the Most Similar Relation Diagram. In: Lin, S., Huang, X. (eds) Advances in Computer Science, Environment, Ecoinformatics, and Education. CSEE 2011. Communications in Computer and Information Science, vol 214. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23321-0_64
Download citation
DOI: https://doi.org/10.1007/978-3-642-23321-0_64
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23320-3
Online ISBN: 978-3-642-23321-0
eBook Packages: Computer ScienceComputer Science (R0)