Air and water pollution present significant threats to public health, highlighting the need for precise environmental monitoring methods. Current solutions rely on multisensory systems with limited specificity. Their calibrations often struggle in real-world conditions, resulting in imprecise air and water quality measurements. This paper aim to address the challenge of calibrating non-specific multisensory systems deployed in open periodic environments. A data-driven calibration method is proposed within a Bayesian framework, which considers several sources of uncertainties that are often overlooked in sensor calibration.
The method combines a non-parametric approach, capturing correlations between pollutants and environmental variables, with a parametric method, that maximizes sensor-provided information. Unlike conventional sensor calibration, our method prioritizes the inclusion of input uncertainties and model errors during calibration, providing a comprehensive framework for robust sensor performance.
The theoretical foundations of the non-parametric approach are presented, and the coupling between non-parametric and parametric methods is detailed. The evaluation using synthetic data demonstrates the method’s efficiency and limitations. Then the approach is validated in an experimental use case where a sensor array based on carbon nanotube is calibrated for monitoring ozone and carbon monoxide in an outdoor deployment.
Keywords: Bayesian Framework, Multisensory Systems, Air and Water Pollution, Data-driven Calibration, Uncertainty quantification
Marine Dumon 1; Bérengère Lebental 1; Guillaume Perrin 1
CC-BY 4.0
@article{SMAI-JCM_2024__10__305_0,
author = {Marine Dumon and B\'ereng\`ere Lebental and Guillaume Perrin},
title = {Optimizing {Sensor} {Calibration} in {Open} {Environments:} {A} {Bayesian} {Approach} for {Non-Specific} {Multisensory} {Systems}},
journal = {The SMAI Journal of computational mathematics},
pages = {305--324},
publisher = {Soci\'et\'e de Math\'ematiques Appliqu\'ees et Industrielles},
volume = {10},
year = {2024},
doi = {10.5802/smai-jcm.114},
language = {en},
url = {https://smai-jcm.centre-mersenne.org/articles/10.5802/smai-jcm.114/}
}
TY - JOUR AU - Marine Dumon AU - Bérengère Lebental AU - Guillaume Perrin TI - Optimizing Sensor Calibration in Open Environments: A Bayesian Approach for Non-Specific Multisensory Systems JO - The SMAI Journal of computational mathematics PY - 2024 SP - 305 EP - 324 VL - 10 PB - Société de Mathématiques Appliquées et Industrielles UR - https://smai-jcm.centre-mersenne.org/articles/10.5802/smai-jcm.114/ DO - 10.5802/smai-jcm.114 LA - en ID - SMAI-JCM_2024__10__305_0 ER -
%0 Journal Article %A Marine Dumon %A Bérengère Lebental %A Guillaume Perrin %T Optimizing Sensor Calibration in Open Environments: A Bayesian Approach for Non-Specific Multisensory Systems %J The SMAI Journal of computational mathematics %D 2024 %P 305-324 %V 10 %I Société de Mathématiques Appliquées et Industrielles %U https://smai-jcm.centre-mersenne.org/articles/10.5802/smai-jcm.114/ %R 10.5802/smai-jcm.114 %G en %F SMAI-JCM_2024__10__305_0
Marine Dumon; Bérengère Lebental; Guillaume Perrin. Optimizing Sensor Calibration in Open Environments: A Bayesian Approach for Non-Specific Multisensory Systems. The SMAI Journal of computational mathematics, Volume 10 (2024), pp. 305-324. doi : 10.5802/smai-jcm.114. https://smai-jcm.centre-mersenne.org/articles/10.5802/smai-jcm.114/
[1] Bayesian Sensor Calibration, IEEE Sensors Journal, Volume 22 (2022) no. 20, pp. 19384-19399 | DOI
[2] Electrical and Electrochemical Sensors Based on Carbon Nanotubes for the Monitoring of Chemicals in Water – A Review, Sensors, Volume 22 (2022) no. 1, 218 | DOI
[3] Directive 2008/50/EC of the European Parliament. The council of 21 may 2008 on ambient air quality, and cleaner air for europe, Official Journal of the European Union (2008)
[4] Identification of robust Gaussian Process Regression with noisy input using EM algorithm, Chemometr. Intell. Lab. Syst., Volume 191 (2019), pp. 1-11 | DOI
[5] A review on environmental gas sensors: Materials and technologies, Sensors International, Volume 2 (2021), 100116 | DOI
[6] Feature significance for multivariate kernel density estimation, Comput. Stat. Data Anal., Volume 52 (2008) no. 9, pp. 4225-4242 | DOI | Zbl
[7] Gaussian processes for multi-sensor environmental monitoring, 2015 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), IEEE (2015), pp. 208-213 | DOI
[8] Approximate inference of the bandwidth in multivariate kernel density estimation, Comput. Stat. Data Anal., Volume 55 (2011) no. 12, pp. 3104-3122 | DOI | Zbl
[9] Air pollution and public health: emerging hazards and improved understanding of risk, Environ. Geochem. Health, Volume 37 (2015), pp. 631-649 | DOI
[10] Minimax designs using clustering, J. Comput. Graph. Stat., Volume 27 (2018) no. 1, pp. 166-178 | Zbl
[11] Gaussian Process Training with Input Noise, NIPS’11: Proceedings of the 24th International Conference on Neural Information Processing Systems (J. Shawe-Taylor; R. Zemel; P. Bartlett; F. Pereira; K. Q. Weinberger, eds.), Curran Associates, Inc. (2011), pp. 1341-1349
[12] Wind speed sensor calibration in thermal power plant using Bayesian inference, Case Studies in Thermal Engineering, Volume 19 (2020), 100621 | DOI
[13] Public Health Hazards Due to Unsafe Drinking Water, Air and Water Borne Diseases, Volume 7 (2018)
[14] A repulsion-based method for the definition and the enrichment of opotimized space filling designs in constrained input spaces, J. SFdS, Volume 158 (2017) no. 1, pp. 37-67 | Zbl
[15] Taking into account input uncertainties in the Bayesian calibration of time-consuming simulators, J. SFdS, Volume 160 (2019) no. 2, pp. 24-46 | Numdam | Zbl
[16] Data-driven kernel representations for sampling with an unknown block dependence structure under correlation constraints, Journal of Computational Statistics and Data Analysis, Volume 119 (2018), pp. 139-154 | DOI | Zbl
[17] Uncertainty-Based Calibration Method for Environmental Sensors—Application to Chlorine and pH Monitoring With Carbon Nanotube Sensor Array, IEEE Sensors Journal, Volume 23 (2023) no. 5, pp. 5146-5155 | DOI
[18] Transforming data to a gaussian distribution, Geostatistics Lessons (Jared Deutsch, ed.), R Core Team, 2018 (Retrieved from https://geostatisticslessons.com/lessons/normalscore)
[19] Simulation and the Monte Carlo method, Springer Series in Statistics, John Wiley & Sons, 2008
[20] The design and analysis of computer experiments, Springer Series in Statistics, Springer, 2003 | DOI
[21] Bayesian Neural Network-Based Calibration for Urban Air Quality Sensors, 32nd European Symposium on Computer Aided Process Engineering (Ludovic Montastruc; Stephane Negny, eds.) (Computer Aided Chemical Engineering), Volume 51, Elsevier, 2022, pp. 1549-1554 | DOI
[22] Variational Bayesian calibration of low-cost gas sensor systems in air quality monitoring, Measurement: Sensors, Volume 19 (2022), 100365 | DOI
[23] Regression shrinkage and selection via the lasso, J. R. Stat. Soc., Ser. B, Stat. Methodol., Volume 58 (1989) no. 1, pp. 267-288 | DOI | Zbl
[24] Introduction to nonparametric estimation, Springer Series in Statistics, Springer, 2009 | DOI
[25] Asymptotic statistics, Cambridge University Press, 2000
[26] Leveraging machine learning algorithms to advance low-cost air sensor calibration in stationary and mobile settings, Atmospheric Environment, Volume 301 (2023), 119692 | DOI
[27] Closing the gap on lower cost air quality monitoring: machine learning calibration models to improve low-cost sensor performance, Atmospheric Measurement Techniques Discussions (2017), pp. 1-36 | DOI
[28] Bayesian estimation of adaptive bandwidth matrices in multivariate kernel density estimation, Comput. Stat. Data Anal., Volume 75 (2014), pp. 28-38 | DOI | Zbl
Cited by Sources: