Associated Doctoral Student in the PhD program since 01.09.2010.
advisors
Prof. Dr. Daniel Keim
organisational data
Room
:
C 201a
Tel.
:
+49 (0)7531 / 88-4364
E-mail
:
tatu "at" inf.uni-konstanz.de
project description
Subspace clustering is an important problem in clustering high-dimensional data.
As the number of dimensions grows, traditional clustering methods become
ineffective because meaningful clusters exist only in subsets of dimensions and
because the distances between data items become indiscriminate. Subspace
clustering explores subsets of dimensions instead of all dimensions and detects
clusters which exist within subspaces. Interpreting the results of subspace
clustering algorithms is not trivial because each cluster is characterized by
the subset of dimensions in which it exists, and standard clustering
visualizations do not take this feature into account. Developing a novel
visualization technique which is able to visualize the output of subspace
clustering algorithms is the focus of my work. The visualization should support
the understanding of clusters, data browsing and finding patterns in
high-dimensional data sets.
publications
The following list of publications covers only those, which are or were published during participation at the Graduiertenkolleg / PhD program.
Articles in Journals
2010
Lehmann, D., Albuquerque, G., Eisemann, M., Tatu, A., Keim, D., Schumann, H., Magnor, M., Theisel, H., Visualisierung und Analyse multidimensionaler Datensätze, Informatik Spektrum, Vol. 33, No. 6, pp. 589-600, December 2010. abstract
