Transmission Probability of SARS-CoV-2 in Office Environment Using Artificial Neural Network

Abstract

In this paper, curve-fitting and an artificial neural network (ANN) model were developed to predict R-Event. Expected number of new infections that arise in any event occurring over a total time in any space is termed as R-Event. Real-time data for the office environment was gathered in the spring of 2022 in a naturally ventilated office room in Roorkee, India, under composite climatic conditions. To ascertain the merit of the proposed ANN and curve-fitting models, the performances of the ANN approach were compared against the curve fitting model regarding conventional statistical indicators, i.e., correlation coefficient, root mean square error, mean absolute error, Nash-Sutcliffe efficiency index, mean absolute percentage error, and a20-index. Eleven input parameters namely indoor temperature ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T_{I_n}</i> ), indoor relative humidity ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RH_{I_n}</i> ), area of opening ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A_O</i> ), number of occupants ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ), area per person ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A_P</i> ), volume per person ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V_P</i> ), <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CO</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> concentration ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CO</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ), air quality index ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">AQI</i> ), outer wind speed ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">W_S</i> ), outdoor temperature ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T_Out</i> ), outdoor humidity ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RH_Out</i> ) were used in this study to predict the R-Event value as an output. The primary goal of this research is to establish the link between <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CO</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> concentration and R-Event value; eventually providing a model for prediction purposes. In this case study, the correlation coefficient of the ANN model and curve-fitting model were 0.9992 and 0.9557, respectively. It shows the ANN model’s higher accuracy than the curve-fitting model in R-Event prediction. Results indicate the proposed ANN prediction performance (R=0.9992, RMSE=0.0018708, MAE=0.0006675, MAPE=0.8643816, NS=0.9984365, and a20-index=0.9984300) is reliable and highly accurate to predict the R-event for offices.