Abstract
We present a method to cluster multivariate data according to their density (or any other target function): all observations lying within one “basin” or sitting on the slopes of one “mountain” are assigned to one cluster. The method exploits a neighborhood structure given by the Delaunay triangulation or a k-nearest neighbor graph, and each cluster is given in terms of a basin spanning tree. The root of each basin spanning tree corresponds to a local density maximum, and the trees can be used for simplified representation and visualization of the observations. We compare the accuracy and speed of different approximations, apply the method to real-world data sets and compare its computational complexity to published algorithms.
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
BARBER, C. B., DOBKIN, D. P., and HUHDANPAA, H. (1996): The quickhull algorithm for convex hulls. ACM Trans. Math. Soft., 22(4):469–483. http://www.geom.umn.edu/locate/qhull.
BOCK, H.H. (1974): Automatische Klassifikation. Vandenhoeck & Ruprecht, Gottingen.
CHENG, Y. (1995): Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17:790–799.
DOMENICONI, C. and GUNOPULOS, D. (2001): An efficient approach for approximating multi-dimensional range queries and nearest neighbor classification in large datasets. In Proc. 18th International Conf. on Machine Learning, pages 98–105, San Francisco. Morgan Kaufmann.
FOWLKES, E. B. and MALLOWS, C. L. (1983): A method for comparing two hierarchical clusterings. Journal of the American Statistical Association, 78:553–569.
ESTER, M., KRIEGEL, H.-P., SANDER, J. and XIAOWEI XU (1996): A densitybased algorithm for discovering clusters in large spatial databases with noise. In Proc. 2nd Int. Conf. on Knowledge Discovery and Data Mining (KDD 96), pages 226–231, Portland. AAAI Press.
GODTLIEBSEN, F., MARRON, J. S., and CHAUD (2002): Significance in scale space for bivariate density estimation. Journal of Computational and Graphical Statistics, 11:1–21.
HAMPRECHT, F. A., PETER, C., DAURA, X., THIEL, W., and VAN GUNSTEREN, W. F. (2001): A strategy for analysis of (molecular) equilibrium simulations: configuration space density estimation, clustering and visualization. J. Chem. Phys., 114:2079–2089.
HINNEBURG, A. and KEIM, D. A. (1998): An efficient approach to clustering in multimedia databases with noise. In Proc. 4th Int. Conf. on Knowledge Discovery and Data Mining (KDD 98), pages 58–65, New York. AAAI Press.
KOWALEWSKI, F. (1995): A gradient procedure for determining clusters of relatively high point density. Pattern Recognition, 28:1973–1984.
MERKWIRTH, C., PARLITZ, U., and LAUTERBORN, W. (2000): Fast exact and approximate nearest neighbor searching for nonlinear signal processing. Physical Review E, 62:2089–2097.
SCOTT, D. W. (1992): Multivariate Density Estimation. Wiley, New York.
SILVERMAN, B. W. (1986): Density Estimation for Statistics and Data Analysis. Monographs on Statistics and Applied Probability. Chapman & Hall.
WEHRENS, R., SIMONETTI, A. W., and BUYDENS, L. M. C. (2001): Mixture modelling of medical magnetic resonance data. Journal of Chemometrics, 16:1–10.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hader, S., Hamprecht, F.A. (2003). Efficient Density Clustering Using Basin Spanning Trees. In: Schader, M., Gaul, W., Vichi, M. (eds) Between Data Science and Applied Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18991-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-18991-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40354-8
Online ISBN: 978-3-642-18991-3
eBook Packages: Springer Book Archive