Stochastic Comparison of Machine Learning Approaches to Calibration of Mobile Air Quality Monitors

  • E. Esposito
  • S. De Vito
  • M. Salvato
  • G. Fattoruso
  • V. Bright
  • R. L. Jones
  • O. Popoola
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 431)

Abstract

Recently, the interest in the development of new pervasive or mobile implementations of air quality multisensor devices has significantly grown. New application opportunities appeared together with new challenges due to limitations in dealing with rapid pollutants concentrations transients both for static and mobile deployments. Sensors dynamic is one of the primary factor in limiting the capability of the device of estimating true concentration when it is rapidly changing. Researchers have proposed several approaches to these issues but none have been tested in real conditions. Furthermore, no performance comparison is currently available. In this contribution, we propose and compare different approaches to the calibration problem of novel fast air quality multisensing devices, using two datasets recorded in field. Machine learning architectures have been designed, optimized and tested in order to tackle the cross sensitivities issues and sensors inherent dynamic limitations to perform accurate prediction and uncertainty estimation. Comparison results shows the advantage of dynamic non linear architectures versus static linear ones with support vector regressors scoring best results.

Keywords

Air quality Chemical sensors Calibration Mobile air quality monitoring Machine learning 

Notes

Acknowledgements

This work was partially funded by project MAVER (Manutenzione Avanzata dei Veicoli Regionali) under Campania Aerospace District initiative and by COST Action TD1105 EuNetAir (European Network on New Sensing Technologies for Air-Pollution Control and Environmental Sustainability).

References

  1. 1.
    Directive 2008/50/EC of the European Parliament and of the Council on ambient air quality and cleaner air for Europe, Official Journal of European Union, L152/1, 6/2008Google Scholar
  2. 2.
    I. Mead et al., The use of electrochemical sensors for monitoring urban air quality in low-cost, high-density networks. Atmos. Environ. 70, 186–203 (2013)CrossRefGoogle Scholar
  3. 3.
    L. Capezzuto et al., A maker friendly mobile and social sensing approach to urban air quality monitoring, in IEEE SENSORS 2014 Proceedings (Valencia, 2014), pp. 12–16Google Scholar
  4. 4.
    L. Spinelle et al., Field calibration of a cluster of low-cost available sensors for air quality monitoring. Part A: Ozone and nitrogen dioxide. Sens. Actuators B Chem. 215, 249–257 (2015)CrossRefGoogle Scholar
  5. 5.
    J. Fonollosa et al., Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring. Sens. Actuators B Chem. 215, 618–629 (2015)CrossRefGoogle Scholar
  6. 6.
    E. Esposito et al., Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems. Sens. Actuators B Chem. 231, 701–713 (2016)CrossRefGoogle Scholar
  7. 7.
    J.G. Monroy et al., Probabilistic gas quantification with MOX sensors in open sampling systems—a Gaussian process approach. Sens. Actuators B Chem. 188, 298–312 (2013)CrossRefGoogle Scholar
  8. 8.
    A. Shirzad et al., A comparison between performance of support vector regression and artificial neural network in prediction of pipe burst rate in water distribution networks. KSCE J. Civ. Eng. 18(4), 941–948 (2014)CrossRefGoogle Scholar
  9. 9.
    I. Naquib et al., Support vector regression and artificial neural network models for stability indicating analysis of mebeverine hydrochloride and sulpiride mixtures in pharmaceutical preparation: a comparative study. Spectrochim. Acta A Mol. Biomol. Spectrosc. 86, 515–526 (2012)CrossRefGoogle Scholar
  10. 10.
    R. Balabin et al., Support vector machine regression (SVR/LS-SVM)—an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data. Analyst 136(8), 1703–1712 (2011)CrossRefGoogle Scholar
  11. 11.
    M.C. Ozturk et al., Analysis and design of echo state networks. Neural Computation 19(1), 111–138 (2007)CrossRefMATHGoogle Scholar
  12. 12.
    De Vito et al., CO, NO2 and NOx urban pollution monitoring with on-field calibrated electronic nose by automatic bayesian regularization. Sens. Actuators B Chem. 143(1), 182–191 (2009). UCI datasetCrossRefGoogle Scholar
  13. 13.

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • E. Esposito
    • 1
  • S. De Vito
    • 1
  • M. Salvato
    • 1
  • G. Fattoruso
    • 1
  • V. Bright
    • 2
  • R. L. Jones
    • 2
  • O. Popoola
    • 2
  1. 1.DTE-FSN-DINENEAPorticiItaly
  2. 2.Department of ChemistryUniversity of CambridgeCambridgeUK

Personalised recommendations