« Previous AbstractIdentification of ammonium source for groundwater in the piedmont zone with strong runoff of the Hohhot Basin based on nitrogen isotope    Next AbstractA novel non-invasive exhaled breath biopsy for the diagnosis and screening of breast cancer »

Build Simul

Title:		Machine learning approach for estimating the human-related VOC emissions in a university classroom
Author(s):		Liu J; Zhang R; Xiong J;
Address:		"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, 100081 China. GRID: grid.43555.32. ISNI: 0000 0000 8841 6246 Department of Environmental Science, Policy and Management, University of California, Berkeley, CA 94720 USA. GRID: grid.47840.3f. ISNI: 0000 0001 2181 7878 State Key Laboratory of Green Building in Western China, Xi'an University of Architecture and Technology, Xi'an, 710055 China. GRID: grid.440704.3. ISNI: 0000 0000 9796 4826"
Journal Title:		Build Simul
Year:		2023
Volume:		20230313
Issue:		6
Page Number:		915 - 925
DOI:		10.1007/s12273-022-0976-y
ISSN/ISBN:		1996-3599 (Print) 1996-8744 (Electronic) 1996-3599 (Linking)
Abstract:		"Indoor air quality becomes increasingly important, partly because the COVID-19 pandemic increases the time people spend indoors. Research into the prediction of indoor volatile organic compounds (VOCs) is traditionally confined to building materials and furniture. Relatively little research focuses on estimation of human-related VOCs, which have been shown to contribute significantly to indoor air quality, especially in densely-occupied environments. This study applies a machine learning approach to accurately estimate the human-related VOC emissions in a university classroom. The time-resolved concentrations of two typical human-related (ozone-related) VOCs in the classroom over a five-day period were analyzed, i.e., 6-methyl-5-hepten-2-one (6-MHO), 4-oxopentanal (4-OPA). By comparing the results for 6-MHO concentration predicted via five machine learning approaches including the random forest regression (RFR), adaptive boosting (Adaboost), gradient boosting regression tree (GBRT), extreme gradient boosting (XGboost), and least squares support vector machine (LSSVM), we find that the LSSVM approach achieves the best performance, by using multi-feature parameters (number of occupants, ozone concentration, temperature, relative humidity) as the input. The LSSVM approach is then used to predict the 4-OPA concentration, with mean absolute percentage error (MAPE) less than 5%, indicating high accuracy. By combining the LSSVM with a kernel density estimation (KDE) method, we further establish an interval prediction model, which can provide uncertainty information and viable option for decision-makers. The machine learning approach in this study can easily incorporate the impact of various factors on VOC emission behaviors, making it especially suitable for concentration prediction and exposure assessment in realistic indoor settings"
Keywords:		human-related VOCs indoor air quality interval prediction kernel density estimation (KDE) least squares support vector machine (LSSVM) machine learning;
Notes:		"PubMed-not-MEDLINELiu, Jialong Zhang, Rui Xiong, Jianyin eng China 2023/05/17 Build Simul. 2023; 16(6):915-925. doi: 10.1007/s12273-022-0976-y. Epub 2023 Mar 13"