Articles | Volume 14, issue 2
https://doi.org/10.5194/jsss-14-119-2025
https://doi.org/10.5194/jsss-14-119-2025
Regular research article
 | 
04 Jul 2025
Regular research article |  | 04 Jul 2025

Domain shifts in industrial condition monitoring: a comparative analysis of automated machine learning models

Payman Goodarzi, Andreas Schütze, and Tizian Schneider

Related authors

Efficient hardware implementation of interpretable machine learning based on deep neural network representations for sensor data processing
Julian Schauer, Payman Goodarzi, Andreas Schütze, and Tizian Schneider
J. Sens. Sens. Syst., 14, 169–185, https://doi.org/10.5194/jsss-14-169-2025,https://doi.org/10.5194/jsss-14-169-2025, 2025
Short summary

Related subject area

Measurement systems: Sensor signal processing and electronics
Efficient hardware implementation of interpretable machine learning based on deep neural network representations for sensor data processing
Julian Schauer, Payman Goodarzi, Andreas Schütze, and Tizian Schneider
J. Sens. Sens. Syst., 14, 169–185, https://doi.org/10.5194/jsss-14-169-2025,https://doi.org/10.5194/jsss-14-169-2025, 2025
Short summary
Suppression of polarization random noise in a two-dimensional force sensorbased on random forest
Jian Liu
J. Sens. Sens. Syst., 14, 1–11, https://doi.org/10.5194/jsss-14-1-2025,https://doi.org/10.5194/jsss-14-1-2025, 2025
Short summary
A portable biosensor for simultaneous diagnosis of TNF-α and IL-1β in saliva biomarkers using twin electronic devices
Majid Monajjemi, Fatemeh Mollaamin, Motahareh Dehghandar, Sara Shahriari, Parisa Latifi, and Samira Mohammadi
J. Sens. Sens. Syst., 13, 245–261, https://doi.org/10.5194/jsss-13-245-2024,https://doi.org/10.5194/jsss-13-245-2024, 2024
Short summary
Extraction of nanometer-scale displacements from noisy signals at frequencies down to 1 mHz obtained by differential laser Doppler vibrometry
Dhyan Kohlmann, Marvin Schewe, Hendrik Wulfmeier, Christian Rembe, and Holger Fritze
J. Sens. Sens. Syst., 13, 167–177, https://doi.org/10.5194/jsss-13-167-2024,https://doi.org/10.5194/jsss-13-167-2024, 2024
Short summary
Simple in-system control of microphone sensitivities in an array
Artem Ivanov
J. Sens. Sens. Syst., 13, 81–88, https://doi.org/10.5194/jsss-13-81-2024,https://doi.org/10.5194/jsss-13-81-2024, 2024
Short summary

Cited articles

Atanov, A., Filatov, A., Yeo, T., Sohmshetty, A., and Zamir, A.: Task discovery: Finding the tasks that neural networks generalize on, Adv. Neur. In., 35, 15702–15717, 2022. a
Avci, O., Abdeljaber, O., Kiranyaz, S., Hussein, M., Gabbouj, M., and Inman, D. J.: A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications, Mech. Syst. Signal Pr., 147, 107077, https://doi.org/10.1016/j.ymssp.2020.107077, 2021. a, b, c
Bastuck, M., Leidinger, M., Sauerwald, T., and Schütze, A.: Improved quantification of naphthalene using non-linear Partial Least Squares Regression, ISOEN, arXiv [preprint], https://doi.org/10.48550/arXiv.1507.05834, 21 July 2015. a
Bellman, R. E.: Adaptive Control Processes, Princeton University Press, Princeton, ISBN 9781400874668, https://doi.org/10.1515/9781400874668, 1961. a
Buckley, T., Ghosh, B., and Pakrashi, V.: A Feature Extraction & Selection Benchmark for Structural Health Monitoring, Struct. Health Monit., 22, 2082–2127, https://doi.org/10.1177/14759217221111141, 2022. a
Download
Short summary
Selecting the best model for monitoring industrial machines is challenging due to limited data and varying conditions. While deep learning (DL) is often considered ideal, it does not always perform well. We compared DL with traditional methods focused on feature extraction and classification. Our tests on seven datasets revealed that traditional methods are more reliable when machine conditions change, highlighting the importance of simpler, interpretable models for industrial monitoring.
Share