Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Processing hyperspectral data in machine learning

 
: Villmann, Thomas; Kästner, Marika; Backhaus, Andreas; Seiffert, Udo

Verleysen, M. ; Katholieke Universiteit, Leuven:
21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013 : Bruges, Belgium, April 24 - 25 - 26, 2013
Louvain-la-Neuve: Ciaco, 2013
ISBN: 2-87419-081-0
ISBN: 978-2-87419-081-0
10 pp.
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) <21, 2013, Bruges>
English
Conference Paper
Fraunhofer IFF ()

Abstract
The adaptive and automated analysis of hyperspectral data is mandatory in many areas of research such as physics, astronomy and geophysics, chemistry, bioinformatics, medicine, biochemistry, engineering, and others. Hyperspectra dier from other spectral data that a large fre- quency range is uniformly sampled. The resulting discretized spectra have a huge number of spectral bands and can be seen as good approximations of the underlying continuous spectra. The large dimensionality causes nu- merical diculties in ecient data analysis. Another aspect to deal with is that the amount of data may range from several billion samples in geo- physics to only a few in medical applications. In consequence, dedicated machine learning algorithms and approaches are required for precise while efficient processing of hyperspectral data, which should include also expert knowledge of the application domain as well as mathematical properties of the hyperspectral data.

: http://publica.fraunhofer.de/documents/N-292896.html