Clustering Methods in Geometric Modeling and Scientific Visualization Dr. Hans Hagen University of Kaiserslautern Germany Tuesday, September 8, 2009 11:00 a.m. - 12:00 p.m. Fuller Labs 320 Clustering and classification of datasets is an important problem in many application fields; it is most often used to determine specific regions of interest. In Geometric Modeling and Scientific Visualization, clustering methods based on generalized Voronoi Diagrams have developed over the last couple of years into standard techniques. Commonly, the topology of the dataset has to be preserved, implying that unconnected parts of a cluster (so-called holes) have to be avoided. We have developed a new Voronoi clustering technique based on the k-means scheme. For this purpose, we construct generalized distance functions that guarantee topological correctness. The distance functions are given by a custom definition of the unit neighborhood of seed points. Using a region-growing algorithm that is independent of the distance function used and specific weighting, we arrive at a flexible and general topology-preserving clustering method. We apply our scheme to both multi-dimensional and scattered data examples from simulation based modeling and in urban planning. However, the domain independent algorithm can easily be used in many other clustering and classification tasks. ______ Hans Hagen received the BS and MS degrees from the University of Freiburg and the PhD degree from the University of Dortmund. He is currently a professor in the Department of Computer Sciences at the University of Kaiserslautern, Germany, and heads the research group for Computer Graphics and Computer Geometry. He is both national and international pioneer in his research domains of Geometric Modeling and Scientific Visualization. Additionally, his scientific interests cover the domains of Computer Graphics and Computer Aided Geometric Design. He has received several offers, among them Dean and Chairman Positions at prominent American universities. His scientific work includes more than 250 refereed publications and 15 books. Host: Prof. Matthew Ward Refreshments will be served. Maintained by webmaster@cs.wpi.edu Last modified: August 19, 2009

Department of Computer Science - Worcester Polytechnic Institute
100 Institute Road, Worcester, MA 01609-2280
Phone: +1-508-831-5357 - Fax: +1-508-831-5776 - cs@wpi.edu