Analyzing high-dimensional data by subspace validity

Author

Amir, Amihood ; Kashi, Reuven ; Netanyahu, Nathan S. ; Keim, Daniel ; Wawryniuk, Markus

Author_Institution

Dept. of Comput. Sci., Bar-Ilan Univ., Ramat-Gan, Israel

fYear

2003

fDate

19-22 Nov. 2003

Firstpage

473

Lastpage

476

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.

Keywords

feature extraction; image segmentation; statistical testing; visual databases; arbitrary shaped projected clusters; high-dimensional data analysis; noise levels; real data sets; statistical tests; subspace validity; Automation; Clustering algorithms; Computer science; Data analysis; Humans; Information analysis; Noise level; Space technology; Testing; Topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Mining, 2003. ICDM 2003. Third IEEE International Conference on

Print_ISBN

0-7695-1978-4

Type

conf

DOI

10.1109/ICDM.2003.1250955

Filename

1250955

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2370101