Investigation of Audio Feature Application for CO2 Sensor-Based Occupancy Detection Enhancement

Marija Skromule, Rainers Kozlovskis, Deniss Tiscenko, Janis Judvaitis. Investigation of Audio Feature Application for CO2 Sensor-Based Occupancy Detection Enhancement. Buildings, MDPI, 2026.

Bibtex citāts:
@article{20912_2026,
author = {Marija Skromule and Rainers Kozlovskis and Deniss Tiscenko and Janis Judvaitis},
title = {Investigation of Audio Feature Application for CO2 Sensor-Based Occupancy Detection Enhancement},
journal = {Buildings},
publisher = {MDPI},
year = {2026}
}

Anotācija: This study investigates the integration of audio features with CO2 sensor data to enhance occupancy detection accuracy in naturally ventilated office environments. Accurate occupancy detection is pivotal for smart building energy management, yet CO2-based methods cannot provide fast enough response times and are sensitive to air circulation changes due to internal convection. In this article we propose a combination of CO2 sensors and audio features from MEMS microphones to improve the occupancy detection accuracy and improve the response times. We use a Random Forest classifier and evaluate the results across two scenarios: CO2-only and CO2 combined with audio features. Results show that incorporating the audio features into the occupancy detection algorithms yields a significant increase in detection accuracy and speed, especially when the environment is subject to frequent air circulation changes due to internal convection, like the opening and closing of windows and doors. Combining the CO2 and audio sensing offers a promising, cost-effective approach to occupancy detection in smart buildings, yet more research on advanced audio processing and feature selection is necessary.

URL: https://www.mdpi.com/2075-5309/16/3/545