Estimation of Occupancy Using IoT Sensors and a Carbon Dioxide-Based Machine Learning Model with Ventilation System and Differential Pressure Data

Abstract

Infectious diseases such as the COVID-19 pandemic have necessitated preventive measures against the spread of indoor infections. There has been increasing interest in indoor air quality (IAQ) management. Air quality can be managed simply by alleviating the source of infection or pollution, but the person within a space can be the source of infection or pollution, thus necessitating an estimation of the exact number of people occupying the space. Generally, management plans for mitigating the spread of infections and maintaining the IAQ, such as ventilation, are based on the number of people occupying the space. In this study, carbon dioxide (CO2)-based machine learning was used to estimate the number of people occupying a space. For machine learning, the CO2 concentration, ventilation system operation status, and indoor–outdoor and indoor–corridor differential pressure data were used. In the random forest (RF) and artificial neural network (ANN) models, where the CO2 concentration and ventilation system operation modes were input, the accuracy was highest at 0.9102 and 0.9180, respectively. When the CO2 concentration and differential pressure data were included, the accuracy was lowest at 0.8916 and 0.8936, respectively. Future differential pressure data will be associated with the change in the CO2 concentration to increase the accuracy of occupancy estimation.

Keywords

• internet of things sensor
• differential pressure
• carbon dioxide
• occupancy
• ventilation system
• machine learning