首页|University of Belgrade Reports Findings in Machine Learning (Unveiling the poten tial of a novel portable air quality platform for assessment of fine and coarse particulate matter: in-field testing, calibration, and machine learning insights )
University of Belgrade Reports Findings in Machine Learning (Unveiling the poten tial of a novel portable air quality platform for assessment of fine and coarse particulate matter: in-field testing, calibration, and machine learning insights )
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating in Belgrade, Serb ia, by NewsRx journalists, research stated, “Although low-cost air quality senso rs facilitate the implementation of denser air quality monitoring networks, enab ling a more realistic assessment of individual exposure to airborne pollutants, their sensitivity to multifaceted field conditions is often overlooked in labora tory testing. This gap was addressed by introducing an in-field calibration and validation of three PAQMON 1.0 mobile sensing low-cost platforms developed at th e Mining and Metallurgy Institute in Bor, Republic of Serbia.” The news reporters obtained a quote from the research from the University of Bel grade, “A configuration tailored for monitoring PM and PM mass concentrations al ong with meteorological parameters was employed for outdoor measurement campaign s in Bor, spanning heating (HS) and non-heating (NHS) seasons. A statistically s ignificant positive linear correlation between raw PM and PM measurements during both campaigns (R > 0.90, p 0.001) was observed. Measur ements obtained from the uncalibrated NOVA SDS011 sensors integrated into the PA QMON 1.0 platforms exhibited a substantial and statistically significant correla tion with the GRIMM EDM180 monitor (R > 0.60, p 0.001). The calibration models based on linear and Random Forest (RF) regression were co mpared. RF models provided more accurate descriptions of air quality, with avera ge adjR values for air quality variables in the range of 0.70 to 0.80 and averag e NRMSE values between 0.35 and 0.77. RF-calibrated PAQMON 1.0 platforms display ed divergent levels of accuracy across different pollutant concentration ranges, achieving a data quality objective of 50% during both measurement campaigns.”
BelgradeSerbiaEuropeCyborgsEmerg ing TechnologiesMachine Learning
NETL
NSTL
