Details
| Original language | English |
|---|---|
| Article number | 117097 |
| Journal | Measurement: Journal of the International Measurement Confederation |
| Volume | 250 |
| Publication status | Accepted/In press - Feb 2025 |
Abstract
Addressing sensor drift is essential in industrial measurement systems, where precise data output is necessary for maintaining accuracy and reliability in monitoring processes, as it progressively degrades the performance of machine learning models over time. Our findings indicate that the standard cross-validation method used in existing model training overestimates performance by inadequately accounting for drift. This is primarily because typical cross-validation techniques allow data instances to appear in both training and testing sets, thereby distorting the accuracy of the predictive evaluation. As a result, these models are unable to precisely predict future drift effects, compromising their ability to generalize and adapt to evolving data conditions. This paper presents two solutions: (1) a novel sensor drift compensation learning paradigm for validating models, and (2) automated machine learning (AutoML) techniques to enhance classification performance and compensate sensor drift. By employing strategies such as data balancing, meta-learning, automated ensemble learning, hyperparameter optimization, feature selection, and boosting, our AutoML-DC (Drift Compensation) model significantly improves classification performance against sensor drift. AutoML-DC further adapts effectively to varying drift severities.
Keywords
- Automated machine learning, Sensor measurements, Sensordrift
ASJC Scopus subject areas
- Physics and Astronomy(all)
- Instrumentation
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Measurement: Journal of the International Measurement Confederation, Vol. 250, 117097, 15.06.2025.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Automl for Multi-Class Anomaly Compensation of Sensor Drift
AU - Schaller, Melanie Christine
AU - Kruse, Mathis
AU - Ortega, Antonio
AU - Lindauer, Marius
AU - Rosenhahn, Bodo
N1 - Publisher Copyright: © 2025 The Authors
PY - 2025/2
Y1 - 2025/2
N2 - Addressing sensor drift is essential in industrial measurement systems, where precise data output is necessary for maintaining accuracy and reliability in monitoring processes, as it progressively degrades the performance of machine learning models over time. Our findings indicate that the standard cross-validation method used in existing model training overestimates performance by inadequately accounting for drift. This is primarily because typical cross-validation techniques allow data instances to appear in both training and testing sets, thereby distorting the accuracy of the predictive evaluation. As a result, these models are unable to precisely predict future drift effects, compromising their ability to generalize and adapt to evolving data conditions. This paper presents two solutions: (1) a novel sensor drift compensation learning paradigm for validating models, and (2) automated machine learning (AutoML) techniques to enhance classification performance and compensate sensor drift. By employing strategies such as data balancing, meta-learning, automated ensemble learning, hyperparameter optimization, feature selection, and boosting, our AutoML-DC (Drift Compensation) model significantly improves classification performance against sensor drift. AutoML-DC further adapts effectively to varying drift severities.
AB - Addressing sensor drift is essential in industrial measurement systems, where precise data output is necessary for maintaining accuracy and reliability in monitoring processes, as it progressively degrades the performance of machine learning models over time. Our findings indicate that the standard cross-validation method used in existing model training overestimates performance by inadequately accounting for drift. This is primarily because typical cross-validation techniques allow data instances to appear in both training and testing sets, thereby distorting the accuracy of the predictive evaluation. As a result, these models are unable to precisely predict future drift effects, compromising their ability to generalize and adapt to evolving data conditions. This paper presents two solutions: (1) a novel sensor drift compensation learning paradigm for validating models, and (2) automated machine learning (AutoML) techniques to enhance classification performance and compensate sensor drift. By employing strategies such as data balancing, meta-learning, automated ensemble learning, hyperparameter optimization, feature selection, and boosting, our AutoML-DC (Drift Compensation) model significantly improves classification performance against sensor drift. AutoML-DC further adapts effectively to varying drift severities.
KW - Automated machine learning
KW - Sensor measurements
KW - Sensordrift
UR - http://www.scopus.com/inward/record.url?scp=85219496686&partnerID=8YFLogxK
U2 - 10.1016/j.measurement.2025.117097
DO - 10.1016/j.measurement.2025.117097
M3 - Article
VL - 250
JO - Measurement: Journal of the International Measurement Confederation
JF - Measurement: Journal of the International Measurement Confederation
SN - 0263-2241
M1 - 117097
ER -