4.8 Article

Graph Learning Techniques Using Structured Data for IoT Air Pollution Monitoring Platforms

Journal

IEEE INTERNET OF THINGS JOURNAL
Volume 8, Issue 17, Pages 13652-13663

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2021.3067717

Keywords

Sensors; Pollution measurement; Monitoring; Atmospheric measurements; Air pollution; Laplace equations; Covariance matrices; Air pollution monitoring networks; graph signal processing (GSP); IoT platform; low-cost sensors; signal reconstruction

Funding

  1. National Spanish Fund [PID2019-107910RB-I00]
  2. Secretaria d'Universitats i Recerca de la Generalitat de Catalunya i del Fons Social Europeu
  3. [2017SGR-990]

Ask authors/readers for more resources

The article compares two techniques based on structured data, one based on statistical methods and the other on signal smoothness, as well as a baseline technique that does not rely on measured signal data. The results show that the signal smoothness-based technique performs better than the other two on datasets measuring O-3, NO2, and PM10, and when used together with Laplacian interpolation, it is near optimal compared to linear regression. Additionally, in heterogeneous networks, the reconstruction accuracy is similar to in-situ calibrated sensors, increasing the robustness of the network against sensor failures.
Existing air pollution monitoring networks use reference stations as the main nodes. The addition of low-cost sensors calibrated in-situ with machine learning techniques allows the creation of heterogeneous air pollution monitoring networks. However, current monitoring networks or calibration techniques have limitations in estimating missing data, adding virtual sensors or recalibrating sensors. The use of graphs to represent structured data is an emerging area of research that allows the use of powerful techniques to process and analyze data for air pollution monitoring networks. In this article, we compare two techniques that rely on structured data, one based on statistical methods and the other on signal smoothness, with a baseline technique based on the distance between nodes and that does not rely on the measured signal data. To compare these techniques, the sensor signal is reconstructed with a supervised method based on linear regression and a semisupervised method based on Laplacian interpolation, which allows reconstruction even when data is missing. The results, on data sets measuring O-3, NO2, and PM10, show that the signal smoothness-based technique behaves better than the other two, and used together with the Laplacian interpolation is near optimal with respect to the linear regression method. Moreover, in the case of heterogeneous networks, the results show a reconstruction accuracy similar to the in-situ calibrated sensors. Thus, the use of the network data increases the robustness of the network against possible sensor failures.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available