Articles | Volume 12, issue 1
https://doi.org/10.5194/jsss-12-45-2023
https://doi.org/10.5194/jsss-12-45-2023
Regular research article
 | 
27 Jan 2023
Regular research article |  | 27 Jan 2023

Influence of measurement uncertainty on machine learning results demonstrated for a smart gas sensor

Tanja Dorst, Tizian Schneider, Sascha Eichstädt, and Andreas Schütze

Related authors

Influence of synchronization within a sensor network on machine learning results
Tanja Dorst, Yannick Robin, Sascha Eichstädt, Andreas Schütze, and Tizian Schneider
J. Sens. Sens. Syst., 10, 233–245, https://doi.org/10.5194/jsss-10-233-2021,https://doi.org/10.5194/jsss-10-233-2021, 2021
Short summary

Related subject area

Measurement theory, uncertainty and modeling of measurements: Measurement uncertainty
Towards efficient application-dependent dimensional measurements with computed tomography: optimized reduction of measurement duration using continuous scan mode: experimental investigations
Christian Orgeldinger, Florian Wohlgemuth, Andreas Michael Müller, and Tino Hausotte
J. Sens. Sens. Syst., 11, 219–223, https://doi.org/10.5194/jsss-11-219-2022,https://doi.org/10.5194/jsss-11-219-2022, 2022
Short summary
Structure of digital metrological twins as software for uncertainty estimation
Ivan Poroskun, Christian Rothleitner, and Daniel Heißelmann
J. Sens. Sens. Syst., 11, 75–82, https://doi.org/10.5194/jsss-11-75-2022,https://doi.org/10.5194/jsss-11-75-2022, 2022
Short summary
Assessment of uncertainties for measurements of total near-normal emissivity of low-emissivity foils with an industrial emissometer
Jacques Hameury, Guillaume Failleau, Mariacarla Arduini, Jochen Manara, Elena Kononogova, Albert Adibekyan, Christian Monte, Alexander Kirmes, Eric Palacio, and Holger Simon
J. Sens. Sens. Syst., 10, 135–152, https://doi.org/10.5194/jsss-10-135-2021,https://doi.org/10.5194/jsss-10-135-2021, 2021
Short summary
Measurement uncertainty assessment for virtual assembly
Manuel Kaufmann, Ira Effenberger, and Marco F. Huber
J. Sens. Sens. Syst., 10, 101–108, https://doi.org/10.5194/jsss-10-101-2021,https://doi.org/10.5194/jsss-10-101-2021, 2021
Short summary
Measurements at laser materials processing machines: spectrum deconvolution including uncertainties and model selection
Rolf Behrens, Björn Pullner, and Marcel Reginatto
J. Sens. Sens. Syst., 10, 13–18, https://doi.org/10.5194/jsss-10-13-2021,https://doi.org/10.5194/jsss-10-13-2021, 2021
Short summary

Cited articles

Amann, J., Baur, T., and Schultealbert, C.: Measuring Hydrogen in Indoor Air with a Selective Metal Oxide Semiconductor Sensor: Dataset, Zenodo [data set], https://doi.org/10.5281/zenodo.4593853, 2021a. a
Amann, J., Baur, T., Schultealbert, C., and Schütze, A.: Bewertung der Innenraumluftqualität über VOC-Messungen mit Halbleitergassensoren - Kalibrierung, Feldtest, Validierung, tm - Tech. Mess., 88, S89–S94, https://doi.org/10.1515/teme-2021-0058, 2021b. a
Asikainen, A., Carrer, P., Kephalopoulos, S., Fernandes, E. d. O., Wargocki, P., and Hänninen, O.: Reducing burden of disease from residential indoor air exposures in Europe (HEALTHVENT project), Environ. Health, 15, S35, https://doi.org/10.1186/s12940-016-0101-8, 2016. a
Baur, T., Schütze, A., and Sauerwald, T.: Optimierung des temperaturzyklischen Betriebs von Halbleitergassensoren, tm - Tech. Mess., 82, 187–195, https://doi.org/10.1515/teme-2014-0007, 2015. a
Baur, T., Amann, J., Schultealbert, C., and Schütze, A.: Field Study of Metal Oxide Semiconductor Gas Sensors in Temperature Cycled Operation for Selective VOC Monitoring in Indoor Air, Atmosphere, 12, 647, https://doi.org/10.3390/atmos12050647, 2021. a, b, c
Download
Short summary
A fundamental problem of machine learning (ML) is measurement uncertainty and the influence on ML results. Measurement uncertainty, which is critical in hazardous gas detection, is directly addressed in this paper. A previously published toolbox is extended for regression. One of the benefits of this approach is obtaining a better understanding of where the overall system should be improved. This can be achieved by either improving the trained ML model or using a sensor with higher precision.