Analyzing High-Dimensional Data by Subspace Validity

Third IEEE International Conference on Data Mining (ICDM'03) p. 473
Analyzing High-Dimensional Data by Subspace Validity
Amihood Amir, Bar-Ilan University
Reuven Kashi, Bar-Ilan University
Nathan S. Netanyahu, Bar-Ilan University
Daniel Keim, University of Konstanz
Markus Wawryniuk, University of Konstanz

Full Article Text:

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICDM.2003.1250955
Send link to a friend

Abstract
We are proposing a novel method that makes it possible to analyze high dimensional data with arbitrary shaped projected clusters and high noise levels. At the core of our method lies the idea of subspace validity. We map the data in a way that allows us to test the quality of subspaces using statistical tests. Experimental results, both on synthetic and real data sets, demonstrate the potential of our method.
Back to Top Additional Information
Citation: Amihood Amir, Reuven Kashi, Nathan S. Netanyahu, Daniel Keim, Markus Wawryniuk, "Analyzing High-Dimensional Data by Subspace Validity," icdm, p. 473, Third IEEE International Conference on Data Mining (ICDM'03), 2003

	Advanced Search
CS Search Google Search