Description
IoT sensors are extensively used in monitoring, detection and early warning contexts. They rely on a tight integration of sensory inputs and embedded data processing to autonomously cope with disturbances and unpredictability of the physical world. Air quality monitoring presents an interesting and challenging use-case for the IoT technology to provide sustainable and reliable measurements as well as accurate predictions. On the one hand, miniaturised chemical gas sensors require frequent recalibration, are power hungry or come with slow response times. Using these in large scale deployments is problematic due to high maintenance costs to replace batteries and reference-measure sensors’ signals. On the other hand, gathered datasets are sparse: they comprise only point measurements and require well-designed spatiotemporal prediction models to yield accurate forecasts. These forecasts are valuable for large-scale optimizations and control of local pollution sources to improve ambient air quality, in particular in urban areas.In this talk, I will summarise my lessons learned from operating and modelling low-cost IoT sensors for air quality monitoring over the past 10 years and present recent research findings on how to make such measurement networks more sustainable, and the short-term forecasts obtained from measurement data more accurate.
Period | 14 Jan 2022 |
---|---|
Event title | 5th IEEE Internet of Things (IoT) Vertical and Topical Summit at RWW2022 |
Event type | Conference |
Location | Las Vegas, Hybrid, United StatesShow on map |
Degree of Recognition | International |
Fields of Expertise
- Information, Communication & Computing
Documents & Links
Related content
-
Projects
-
LocSense - Dependable Localization and Sensing Services for cognitive products
Project: Research project
-
Publications
-
Interpretable and Transferable Models to Understand the Impact of Lockdown Measures on Local Air Quality
Research output: Contribution to conference › Paper › peer-review
-
Compensating Altered Sensitivity of Duty-Cycled MOX Gas Sensors with Machine Learning
Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review
-
TIP-Air: Tracking Pollution Transfer for Accurate Air Quality Prediction
Research output: Contribution to conference › Paper › peer-review