Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

One-class Autoencoder approach to classify Raman spectra outliers

 
: Hofer-Schmitz, K.; Nguyen, P.-H.; Berwanger, K.

Verleysen, M.:
26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2018 : Bruges, Belgium, April 25, 26, 27, 2018 : proceedings
Louvain-la-Neuve: Ciaco, 2018
ISBN: 978-2-87587-047-6
ISBN: 978-2-87587-048-3
pp.189-194
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) <26, 2018, Bruges>
English
Conference Paper
Fraunhofer FIT ()

Abstract
We present an one-class Anomaly detector based on (deep) Autoencoder for Raman spectra. Omitting preprocessing of the spectra, we use raw data of our main class to learn the reconstruction, with many typical noise sources automatically reduced as the outcome. To separate anomalies from the norm class, we use several, independent statistical metrics for a majority voting. Our evaluation shows a f1-score of up to 99% success.

: http://publica.fraunhofer.de/documents/N-581684.html