Exploring the potential relationship between indoor air quality and the concentration of airborne culturable fungi: a combined experimental and neural network modeling study

Abstract

Indoor airborne culturable fungi exposure has been closely linked to occupants' health. However, conventional measurement of indoor airborne fungal concentration is complicated and usually requires around one week for fungi incubation in laboratory. To provide an ultra-fast solution, here, for the first time, a knowledge-based machine learning model is developed with the inputs of indoor air quality data for estimating the concentration of indoor airborne culturable fungi. To construct a database for statistical analysis and model training, 249 data groups of air quality indicators (concentration of indoor airborne culturable fungi, indoor/outdoor PM and PM concentrations, indoor temperature, indoor relative humidity, and indoor CO concentration) were measured from 85 residential buildings of Baoding (China) during the period of 2016.11.15-2017.03.15. Our results show that artificial neural network (ANN) with one hidden layer has good prediction performances, compared to a support vector machine (SVM). With the tolerance of ± 30%, the prediction accuracy of the ANN model with ten hidden nodes can at highest reach 83.33% in the testing set. Most importantly, we here provide a quick method for estimating the concentration of indoor airborne fungi that can be applied to real-time evaluation.

Comparison of the performance of ITS1 and ITS2 as barcodes in amplicon-based sequencing of bioaerosols

“…Historically, fungi have been identified based on the morphological characteristics of pure cultures in agar media. This process has also been used in more recent exposure studies (Sanchez-Monedero & Stentiford, 2003;Taha et al, 2006;Schlosser et al, 2012;Park et al, 2013;Ghiasian, Maghood & Aghamirian, 2017;Liu et al, 2018). However, most fungal species are difficult to isolate using common culture methods.…”

Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis

“…A review of the literature shows that ANN and SVM have been used in other applications demonstrating the general acceptance of these techniques in different applications of classification tasks (Liu et al, 2018; Li et al, 2017). Therefore, in the present study, ANN and SVM, as the most popular and successful (Sammut & Webb, 2011) methods of machine learning, were also selected for sleep scoring.…”

Experimental Investigation into the Effect of Oil Injection on the Performance of a Variable Speed Twin-Screw Compressor

“…The heat transfer correlation between the air and lubricating oil can be expressed by Equation (6) [22]: The Reynolds number Re and Pr number can be determined by Equations (7) and (8), respectively:…”

“…The compressor efficiency was mainly dependent on the compressor pressure ratio. Liang et al [17][18][19][20][21][22] investigated the application of frequency conversion technology in air compressor control systems and discussed the advantages and disadvantages of these technologies in compressor applications. The study [23][24][25][26][27][28] demonstrated the significance of employing frequency conversion technology in the compressor industry.…”