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

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 PM2.5 and PM10 concentrations, indoor temperature, indoor relative humidity, and indoor CO2 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.

[1]  E. R. Jayaratne,et al.  Indoor aerosols: from personal exposure to risk assessment. , 2013, Indoor air.

[2]  Hao Li,et al.  Quick Estimation Model for the Concentration of Indoor Airborne Culturable Bacteria: An Application of Machine Learning , 2017, International journal of environmental research and public health.

[3]  Zhijian Liu,et al.  Design of high-performance water-in-glass evacuated tube solar water heaters by a high-throughput screening based on machine learning: A combined modeling and experimental study , 2017 .

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  J. Gangneux,et al.  Rapid quantification of viable fungi in hospital environments: analysis of air and surface samples using solid-phase cytometry. , 2013, The Journal of hospital infection.

[6]  Zhe George Zhang,et al.  Forecasting stock indices with back propagation neural network , 2011, Expert Syst. Appl..

[7]  Yuexia Sun,et al.  Associations of dwelling characteristics, home dampness, and lifestyle behaviors with indoor airborne culturable fungi: On-site inspection in 454 Shanghai residences , 2016 .

[8]  Hao Li,et al.  Comparative Study on Theoretical and Machine Learning Methods for Acquiring Compressed Liquid Densities of 1,1,1,2,3,3,3-Heptafluoropropane (R227ea) via Song and Mason Equation, Support Vector Machine, and Artificial Neural Networks , 2016 .

[9]  Y. Hwang,et al.  Impact of a water-damaged indoor environment on kindergarten student absences due to upper respiratory infection , 2013 .

[10]  D. Wraith,et al.  Floor dust bacteria and fungi and their coexistence with PAHs in Jordanian indoor environments. , 2017, The Science of the total environment.

[11]  Lidia Morawska,et al.  Airborne viable fungi in school environments in different climatic regions A review , 2015 .

[12]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[13]  V. R. Phillips,et al.  Comparison of commonly used samplers with a novel bioaerosol sampler with automatic plate exchange , 1997 .

[14]  Marie Frederiksen,et al.  Impact of dwelling characteristics on concentrations of bacteria, fungi, endotoxin and total inflammatory potential in settled dust , 2015 .

[15]  Zhijian Liu,et al.  Artificial Neural Networks-Based Software for Measuring Heat Collection Rate and Heat Loss Coefficient of Water-in-Glass Evacuated Tube Solar Water Heaters , 2015, PloS one.

[16]  Z. Ouyang,et al.  Concentration and Size Distribution of Culturable Airborne Microorganisms in Outdoor Environments in Beijing, China , 2008 .

[17]  M. Kleinman,et al.  Personal and Ambient Air Pollution is Associated with Increased Exhaled Nitric Oxide in Children with Asthma , 2006, Environmental health perspectives.

[18]  T. Meklin,et al.  Microbial content of house dust samples determined with qPCR. , 2009, The Science of the total environment.

[19]  Kewei Cheng,et al.  Novel Method for Measuring the Heat Collection Rate and Heat Loss Coefficient of Water-in-Glass Evacuated Tube Solar Water Heaters Based on Artificial Neural Networks and Support Vector Machine , 2015 .

[20]  S. Vesper,et al.  Evaluation of rapid DNA extraction methods for the quantitative detection of fungi using real-time PCR analysis. , 2002, Journal of microbiological methods.

[21]  Zhijian Liu,et al.  Application of Artificial Neural Networks for Catalysis: A Review , 2017 .

[22]  W W Nazaroff,et al.  Size-resolved fluorescent biological aerosol particle concentrations and occupant emissions in a university classroom. , 2014, Indoor air.

[23]  Angui Li,et al.  Study on the potential relationships between indoor culturable fungi, particle load and children respiratory health in Xi'an, China , 2014 .

[24]  Hao Li,et al.  Prediction of Zeta Potential of Decomposed Peat via Machine Learning: Comparative Study of Support Vector Machine and Artificial Neural Networks , 2015 .

[25]  Ki Joon Heo,et al.  Effects of human activities on concentrations of culturable bioaerosols in indoor air environments , 2016, Journal of Aerosol Science.

[26]  S. Anagnost,et al.  Indicators of airborne fungal concentrations in urban homes: understanding the conditions that affect indoor fungal exposures. , 2015, The Science of the total environment.

[27]  Zhijian Liu,et al.  Investigation of dust loading and culturable microorganisms of HVAC systems in 24 office buildings in Beijing , 2015 .

[28]  Manish Mishra,et al.  Application of artificial neural network for predicting performance of solid desiccant cooling systems – A review , 2017 .

[29]  Wei Wang,et al.  Characteristics of bacterial and fungal aerosols during the autumn haze days in Xi'an, China , 2015 .

[30]  Pierre Baconnier,et al.  Multivariate analysis comparing microbial air content of an air-conditioned building and a naturally ventilated building over one year , 1997 .

[31]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.