2025 SMSI Bannerklein

P1.9.26 Exploitation of Gas Sensor Dynamics by the use of Echo State Networks

Event
14th International Meeting on Chemical Sensors - IMCS 2012
2012-05-20 - 2012-05-23
Nürnberg/Nuremberg, Germany
Chapter
P1.9 Technology and Application
Author(s)
H. Kobialka - Fraunhofer IAIS, Schloss Birlinghoven (Germany), A. Walte - AIRSENSE Analytics GmbH (Germany)
Pages
1240 - 1242
DOI
10.5162/IMCS2012/P1.9.26
ISBN
978-3-9813484-2-2
Price
free

Abstract

Gas sensor arrays generate sensor data time series containing temporal information like gradients, noise patterns, and delays. We want to exploit temporal dynamics in gas sensor data for improving gas measurement in difficult environments, e.g. freight containers. For supervised training of pattern matching models we use Echo State Networks, a new approach for training large recurrent neural networks.

Download