Interactive bivariate mode trees for visual structure analysis

ABSTRACT

The number of modes in a kernel density estimation of a certain data distribution is strongly dependent on the chosen scale parameter. In this paper, we present an interactive mode tree visualization that allows to visually analyze the modality structure of a data distribution. Due to the branched structure of the bivariate mode tree, composed of many curved arcs in 3D, we need to utilize advanced techniques, including clutter removal through transparency, on demand outlier suppression or preservation, and best views, to improve the legibility of the visualization mapping.

References

1. Artero, A. O., de Oliveira, M. C. F., and Levkowitz, H. 2004. Uncovering clusters in crowded parallel coordinates visualizations. In INFOVIS '04: Proceedings of the IEEE Symposium on Information Visualization, IEEE Computer Society, Washington, DC, USA, 81--88.
2. Bissantz, N., and Holzmann, H. 2007. Estimation of a quadratic regression functional using the sinc kernel. Journal of Statistical Planning and Inference 137, 3, 712--719.
3. Cheng, Y. 1995. Mean shift, mode seeking, and clustering. Pattern Analysis and Machine Intelligence, IEEE Transactions on 17, 8 (Aug.), 790--799.
4. Comaniciu, D., and Meer, P. 2002. Mean shift: a robust approach toward feature space analysis. Pattern Analysis and Machine Intelligence, IEEE Transactions on 24, 5 (August), 603--619.
5. Eilers, P. H. C., and Goeman, J. J. 2004. Enhancing scatter-plots with smoothed densities. Bioinformatics 20, 5, 623--628.
6. Florek, M., and Hauser, H. 2010. Quantitative data visualization with interactive kde aurfaces. In Conference Proceedings of Spring Conference on Computer Graphics, SCCG 2010, 39--47.
7. Hahne, F., Arlt, D., Sauermann, M., Majety, M., Poustka, A., Wiemann, S., and Huber, W. 2006. Statistical methods and software for the analysis of high throughput reverse genetic assays using flow cytometry readouts. Genome Biology 7 (August), R77.
8. Inselberg, A. 1985. The plane with parallel coordinates. The Visual Computer 1, 4 (Dec), 69--91.
9. Jensen, H. W. 1996. Global illumination using photon maps. In Proceedings of the eurographics workshop on Rendering techniques '96, Springer-Verlag, 21--30.
10. Kidwell, P., Lebanon, G., and Cleveland, W. S. 2008. Visualizing incomplete and partially ranked data. IEEE Trans. Vis. Comput. Graph. 14, 6, 1356--1363.
11. Klemelä, J. 2008. Mode trees for multivariate data. Journal of Computational and Graphical Statistics 17, 4 (December), 860--869.
12. Leung, Y., Zhang, J.-S., and Xu, Z.-B. 2000. Clustering by scale-space filtering. Pattern Analysis and Machine Intelligence, IEEE Transactions on 22, 12 (December), 1396--1410.
13. Macaulay, F. R. 1931. The whittaker-henderson method of graduation. In The Smoothing of Time Series, NBER Chapters. National Bureau of Economic Research, Inc., December, 89--99.
14. Maciejewski, R., Woo, I., Chen, W., and Ebert, D. 2009. Structuring feature space: A non-parametric method for volumetric transfer function generation. IEEE Transactions on Visualization and Computer Graphics 15, 6, 1473--1480.
15. Marchette, D. J., and Wegman, E. J. 1997. The filtered mode tree. Journal of Computational and Graphical Statistics 6, 2 (June), 143--159.
16. Minnotte, M. C., and Scott, D. W. 1993. The mode tree: A tool for visualization of nonparametric density features. Journal of Computational and Graphical Statistics 2, 51--68.
17. Minnotte, M. C., Marchette, D. J., and Wegman, E. J. 1998. The bumpy road to the mode forest. Journal of Computational and Graphical Statistics 7, 2 (June), 239--251.
18. Parzen, E. 1962. On estimation of a probability density function and mode. The Annals of Mathematical Statistics 33, 3, 1065--1076.
19. Rosenblatt, M. 1956. Remarks on some non-parametric estimates of a density function. The Annals of Mathematical Statistics 27, 832--837.
20. Scott, D. W., and Sain, S. R. 2004. Multi-dimensional density estimation. Handbook of Statistics 24, 229--263.
21. Silverman, B. W. 1981. Using kernel density estimates to investigate multimodality. Journal of the Royal Statistical Society. Series B (Methodological) 43, 1, 97--99.
22. Statlib. http://lib.stat.cmu.edu/.
23. Turlach, B. A. 1993. Bandwidth selection in kernel density estimation: A review. In CORE and Institut de Statistique, 23--493.
24. Vázquez, P.-P., and Sbert, M. 2003. Fast adaptive selection of best views. In ICCSA'03: Proceedings of the 2003 international conference on Computational science and its applications, Springer-Verlag, Berlin, Heidelberg, 295--305.
25. Ward, M. O., Rundensteiner, E. A., Cui, Q., Xie, Z., Yang, D., Wad, C., and Nguyen, D. Q. XmdvTool. http://davis.wpi.edu/xmdv/.
26. Wegman, E. J. 1990. Hyperdimensional data analysis using parallel coordinates. Journal of the American Statistical Association 85, 411, 664--675.
27. Whittaker, E. T. 1923. On a new method of graduation. Proc. Edinburgh Math. Soc, 41, 63--75.
28. Wyszecki, G., and Stiles, W. S. 1982. Color Science: Concepts and Methods, Quantitative Data and Formulae, 2 ed. Wiley-Interscience, September.

Index Terms

• Computing methodologies

  • Computer graphics

    • Image manipulation

    • Rendering