Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Semantic technology classification - a defence and security case study

 
: Thorleuchter, Dirk; Poel, Dirk van den

:
Postprint urn:nbn:de:0011-n-1910382 (102 KByte PDF)
MD5 Fingerprint: a6b9885c44ffe1d3092df70102063b12
© 2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 22.12.2011


Institute of Electrical and Electronics Engineers -IEEE-:
International Conference on Uncertainty Reasoning and Knowledge Engineering, URKE 2011. Proceedings. Vol.1 : 4-7 August 2011, Bali, Indonesia
Piscataway/NJ: IEEE, 2011
ISBN: 978-1-4244-9985-4 (Print)
ISBN: 978-1-4244-9983-0
S.36-39
International Conference on Uncertainty Reasoning and Knowledge Engineering (URKE) <1, 2011, Bali>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer INT ()
text mining; web mining; text classification; defense; security; technology; taxonomy; machine learning; multi label classification

Abstract
In the last years, an increasing collaboration between defense and (civil) security, especially in technological areas can be observed. Here, an approach that automatically extracts relationships among defense - based technologies and security - based technologies is introduced. Information about these relationships can be used as planning support to defense and security - based technological research planners specifically for collaboration decisions. This approach uses machine learning techniques as supervised learning methods and a multi-label text classification algorithm to identify related technologies in different technological lists or taxonomies. Additionally, a web mining approach is used to create training examples. Similarities are computed by use of Jaccard's coefficient and by use of the fuzzy alpha cut method. Further, this approach uses standard text mining methods to prepare unstructured textual information.

: http://publica.fraunhofer.de/dokumente/N-191038.html