Modelling calibration uncertainty in networks of environmental sensors

Simple item page
dc.contributor.authorThomas Smith, Michael
dc.contributor.authorRoss, Magnus
dc.contributor.authorSsematimba, Joel
dc.contributor.authorAlvarado, Pablo A.
dc.contributor.authorÁlvarez, Mauricio
dc.contributor.authorBainomugisha, Engineer
dc.contributor.authorWilkinson, Richard
dc.date.accessioned2023-01-26T21:07:52Z
dc.date.available2023-01-26T21:07:52Z
dc.date.issued2022
dc.description.abstractNetworks of low-cost sensors are becoming ubiquitous, but often suffer from poor accuracies and drift. Regular colocation with reference sensors allows recalibration but is complicated and expensive. Alternatively the calibration can be transferred using low-cost, mobile sensors. However inferring the calibration (with uncertainty) becomes difficult. We propose a variational approach to model the calibration across the network. We demonstrate the approach on synthetic and real air pollution data, and find it can perform better than the state of the art (multi-hop calibration). We extend it to categorical data produced by citizen-scientist labelling. In Summary: The method achieves uncertainty quantified calibration, which has been one of the barriers to low-cost sensor deployment and citizen-science research.en_US
dc.identifier.citationSmith, M. T., Ross, M., Ssematimba, J., Alvarado, P. A., Alverez, M., Bainomugisha, E., & Wilkinson, R. (2022). Modelling calibration uncertainty in networks of environmental sensors. arXiv preprint arXiv:2205.01988.en_US
dc.identifier.urihttps://arxiv.org/abs/2205.01988
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/7298
dc.language.isoenen_US
dc.publisherarXiv preprint arXiven_US
dc.subjectair pollution, Bayesian modelling, calibration, Gaussian processes, low-cost sensors, variational inferenceen_US
dc.titleModelling calibration uncertainty in networks of environmental sensorsen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Modelling calibration uncertainty in networks of pdf.pdf
Size:
3.97 MB
Format:
Adobe Portable Document Format
Description:
Article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Engineering and Technology