Please use this identifier to cite or link to this item: doi:10.22028/D291-37538
Volltext verfügbar? / Dokumentlieferung
Title: Machine Learning based calibration time reduction for Gas Sensors in Temperature Cycled Operation
Author(s): Robin, Yannick
Goodarzi, Payman
Baur, Tobias
Schultealbert, Caroline
Schütze, Andreas
Schneider, Tizian
Language: English
Title: To measure is to know : I2MTC 2021 : IEEE International Instrumentation and Measurement Technology Conference : May 17-21, 2021, virtual conference : 2021 conference proceedings
Pages: 1-6
Publisher/Platform: IEEE
Year of Publication: 2021
Place of publication: Piscataway
Place of the conference: Glasgow, United Kingdom
Free key words: Temperature measurement
Temperature sensors
Volatile organic compounds
Semiconductor device modeling
Temperature distribution
Semiconductor device measurement
DDC notations: 600 Technology
Publikation type: Conference Paper
Abstract: This paper shows the opportunities of data preprocessing and how it influences the time required to record a sufficient amount of valid calibration data samples. Specifically, we approach the minimum needed time for calibration from two sides: on the one hand, repetitions are omitted for training one by another to define the lowest number of valid data that is needed for a model to achieve a reasonable accuracy. On the other hand we add samples, that are labeled as valid data points by steady-state detection to the dataset compared to a time-consuming manual annotation. The results will be demonstrated on a dataset of a metal oxide semiconductor gas sensor in temperature cycled operation measuring mixtures of artificial room air containing several volatile organic compounds and quantifying formaldehyde which is carcinogenic and therefore of high concern in indoor environments. The dataset is generated with an automated gas mixing system and then optimized with the help of data pre-processing methods based on steady-state detection, outlier detection and ResNet neural networks. The dataset can be reduced to only 50 % of the original data and is still able to train an artificial neural network with a root mean square error smaller than 25 % compared to the guideline value for formaldehyde concentration defined by the WHO.
DOI of the first publication: 10.1109/I2MTC50364.2021.9459919
URL of the first publication:
Link to this record: urn:nbn:de:bsz:291--ds-375381
ISBN: 978-1-7281-9539-1
Date of registration: 11-Oct-2022
Faculty: NT - Naturwissenschaftlich- Technische Fakultät
Department: NT - Systems Engineering
Professorship: NT - Prof. Dr. Andreas Schütze
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.