Data-Driven Calibration and Reference-Free Drift Detection for Multi-Modal Sensor Systems
Sensors · 06.11.2026 · 26 (21) · 7016
DOI: 10.3390/s26217016 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 06.11.2026. Verfasst von Kishor Arvind Mohandas Sivakumar und 5 weiteren Autor:innen. Beteiligte Einrichtung: Electrical Engineering, Mathematics and Computer Science Department, TU Delft, 2600AA Delft, The Netherlands. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU Commission, EU Project ENACT.
Abstract (Originalsprache)
Low-cost multi-modal sensors make high-resolution exposomic and urban-health monitoring affordable, but their data are only as useful as they are trustworthy. Measurement bias, cross-sensitivity, temporal drift and domain shift between devices and sites erode reliability, and reference instruments are rarely available for every sensor. We present a two-part reliability workflow for this realistic setting, in which reference data exist for only a subset of sensors, and evaluate it on five custom multi-modal devices deployed at two Brussels sites (9 to 68 days of data per device). For calibration, we benchmark Multiple Linear Regression, Elastic Net, Random Forest, Gradient Boosting and a Domain Adversarial Neural Network (DANN) for O3, NO2, PM2.5 and PM10 on the source device and on other devices at the same site and at the other site using MAE, RMSE, R2, bias, device-balanced aggregation and block-bootstrap intervals. Tree ensembles achieve the lowest source-device errors for most pollutants, yet for PM10, they lose their advantage over the uncalibrated sensor when transferred, a caution for any deployment that calibrates on one unit. DANN attains the highest mean Calibration Transfer Ratio in the transfer settings, although with the available device pairs, the differences are not statistically significant. For modalities without a reference, a cross-sensor residual monitor combined with statistical detectors reliably flags injected gradual drift in sensors that can be reconstructed from the others (UV bands, PM1, temperature, humidity and CO), while Lux, pressure and VOC remain harder. The monitor detects cross-sensor inconsistency rather than isolating the faulty sensor, and the results reflect an injected fault model, not real sensor ageing. Together, these results give a transparent, reproducible baseline and clear practical guidance for building trustworthy low-cost sensor networks.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Electrical Engineering, Mathematics and Computer Science Department, TU Delft, 2600AA Delft, The Netherlands.
- Department of Electronics and Informatics, Vrije Universiteit Brussel, 1050 Brussels, Belgium.
- Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, Kharagpur 721302, India.
- Skynetics Pvt. Ltd., Bangalore 560003, India.
ORCID-Profile: Laurent Segers, Bruno da Silva, Argha Sen, R R Venkatesha Prasad
Förderung
- EU Commission
- EU Project ENACT
Zitieren
APA
Mohandas Sivakumar, K. A., Segers, L., da Silva, B., Sen, A., Narayana, S., & Prasad, R. R. V. (2026). Data-Driven Calibration and Reference-Free Drift Detection for Multi-Modal Sensor Systems. Sensors, 26(21), 7016. https://doi.org/10.3390/s26217016
Vancouver
Mohandas Sivakumar KA, Segers L, da Silva B, Sen A, Narayana S, Prasad RRV. Data-Driven Calibration and Reference-Free Drift Detection for Multi-Modal Sensor Systems. Sensors. 2026;26(21):7016. doi:10.3390/s26217016
BibTeX
@article{MohandasSivakumar2026,
author = {Mohandas Sivakumar, Kishor Arvind and Segers, Laurent and da Silva, Bruno and Sen, Argha and Narayana, Sujay and Prasad, R R Venkatesha},
title = {Data-Driven Calibration and Reference-Free Drift Detection for Multi-Modal Sensor Systems},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {7016},
doi = {10.3390/s26217016}
}
EUVIMED