Search
Efficient Calibration of Cost-Efficient Particulate Matter Sensors Using Machine Learning and Time-Series Alignment
Abstract
Atmospheric particulate matter (PM) poses a significant threat to human health, infiltrating the lungs and brain and leading to severe issues such as heart and lung diseases, cancer, and premature death. The main sources of PM pollution are vehicular and industrial emissions, construction and agricultural activities, and natural phenomena such as wildfires. Research underscores the absence of a safe threshold for particulate exposure, highlighting the crucial need for monitoring PM levels to develop and implement effective risk mitigation measures. Notwithstanding, accurate measurement of PM concentration relies on expensive and cumbersome equipment. Despite the rising popularity of low-cost alternatives, their reliability remains questionable, given their sensitivity to environmental conditions, inherent instability, and manufacturing imperfections. This article proposes a novel approach to efficient correction of low-cost PM sensors. The primary calibration model is a feedforward artificial neural network (ANN), which directly renders predicted output of the corrected sensor based on environmental variables such as temperature, humidity, and atmospheric pressure. The ANN hyper-parameters are identified by aligning time series of prior reference and low-cost sensor readings, which enables the network to learn typical temporal changes of the sensor outcome as a function of the aforementioned parameters as well as operational relationships between the sensor and the reference device. The architecture of the ANN is optimized in terms of the number of neurons in each layer to enhance its generalization capability. Our methodology has been demonstrated using a custom-designed portable monitoring platform and reference data acquired from public stations in Gdansk. The results are indicative of excellent calibration reliability. The achieved correlation coefficients w.r.t. the reference readings are 0.86, 0.88, and 0.72 for PM1, PM10, and PM2.5, respectively, whereas RMSE values are only 3.0, 3.9, and 5.4 µg/m³.
Citations
-
0
CrossRef
-
0
Web of Science
-
0
Scopus
Authors (4)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
KNOWLEDGE-BASED SYSTEMS
no. 295,
pages 1 - 20,
ISSN: 0950-7051 - Language:
- English
- Publication year:
- 2024
- Bibliographic description:
- Kozieł S., Pietrenko-Dąbrowska A., Wójcikowski M., Pankiewicz B.: Efficient Calibration of Cost-Efficient Particulate Matter Sensors Using Machine Learning and Time-Series Alignment// KNOWLEDGE-BASED SYSTEMS -Vol. 295, (2024), s.1-20
- DOI:
- Digital Object Identifier (open in new tab) 10.1016/j.knosys.2024.111879
- Sources of funding:
-
- COST_FREE
- Verified by:
- Gdańsk University of Technology
seen 11 times