Non Parametric Local Density-Based Clustering for Multimodal Overlapping Distributions
In this work, we present a clustering algorithm to find clusters of different sizes, shapes and densities, to deal with overlapping cluster distributions and background noise. The algorithm is divided in two stages. In a first step, local density is estimated at each data point. In a second stage, a hierarchical approach is used by merging clusters according to the introduced cluster distance, based on heuristic measures about how modes overlap in a distribution. Experimental results on synthetic and real databases show the validity of the method.
Unable to display preview. Download preview PDF.
- 1.Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proc. of the second International Conference on Knowledge Discovery and Data Mining, Portland, pp. 226–231 (1996)Google Scholar
- 2.Ertöz, L., Steinbach, M., Kumar, V.: Finding Clusters of Different Sizes, Shapes, and Densities in Noisy, High Dimensional Data. In: Proceedings of Third SIAM International Conference on Data Mining (2003)Google Scholar
- 3.Figueiredo, M., Jain, A.K.: Unsupervised Learning of Mixture Models. IEEE Trans. On PAMI 24(3), 381–396 (2002)Google Scholar
- 5.Guha, S., Rastogi, R., Shim, K.: CURE: An Efficient Clustering Algorithm for Large Databases. In: Proceedings of ACM SIGMOD International Conference on Management of Data, pp. 73–84. ACM, New York (1998)Google Scholar
- 6.Hinneburg, A., Keim, D.A.: An efficient Approach to Clustering in Large Multimedia Databases with Noise. In: Proc. of the ACM SIGKDD (1998)Google Scholar
- 7.Karypis, G., Han, E.H., Kumar, V.: Chameleon: A Hierarchical Clustering Algorithm Using Dynamic Modeling. the IEEE Computer Society 32(8), 68–75 (1999)Google Scholar