Estimation of Human Occupancy in Enclosed Spaces Using CO2 Sensor Data and Statistical Modeling for HVAC Control Applications

초록

This study investigates the estimation of human occupancy in enclosed indoor spaces using CO2 concentration data obtained from a low-cost sensor. An experimental campaign was conducted in a naturally ventilated university classroom, where CO2 levels and the number of occupants were recorded under controlled conditions. Statistical analysis, including linear regression and correlation methods, confirmed a strong positive relationship between occupancy and CO2 accumulation. The selected NDIR sensor (MH-Z16), integrated with an ESP32-based microcontroller, demonstrated sufficient sensitivity and stability for real-time data acquisition. The results validate the use of CO2 concentration as a reliable indirect indicator of human presence, particularly under standardized conditions with minimal external disturbances. The proposed approach offers a cost-effective and scalable solution for demand-controlled ventilation (DCV) in smart building applications, contributing to energy-efficient HVAC control and proactive indoor air quality and workplace safety management.