Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Multi-cluster text mining on the grid using the d-grid UNICORE environment

: Kumpf, K.; Mevissen, T.; Wäldrich, O.; Ziegler, W.; Ginzel, S.; Weuffel, T.

Volltext urn:nbn:de:0011-n-655813 (658 KByte PDF)
MD5 Fingerprint: edd21879657d13c6a4d78b17178b797f
Erstellt am: 10.1.2008

Helmholtz-Gemeinschaft; Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V. -MPG-; Hochschulrektorenkonferenz -HRK-:
German e-Science Conference 2007. Proceedings : 2. - 4. Mai 2007 in Baden-Baden
Baden-Baden, 2007
11 S.
German e-Science Conference (GES) <2007, Baden-Baden>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer SCAI ()

Text mining is inherently more computation-intensive than information retrieval on pre-structured data and requires transfer and filtering of huge amounts of data. Grid environments provide a suitable infrastructure for accomplishing these tasks.
We present the mapping and implementation of a standard text mining (TM) workflow for analysis of biomedical text data from PubMed to a D-Grid UNICORE environment with multiple PC-clusters. We discuss the gain in applicability, the open issues of our solution and possible future enhancements.