Information-theoretic environment features selection for occupancy detection in open office spaces

Abstract

Knowing the presence or the actual number of occupants in a space at any given time is essential for the effective management of various building operation functions such as security and environmental control (e.g., lighting, HVAC). As occupants “interact” with the indoor environment, they will affect environmental conditions through the emission of CO2, heat and sound, and relatively little effort has been reported in the literature on utilizing this environmental sensing data for occupancy detection. This paper presents the findings of a study to address this question by exploring the most effective environmental features for occupancy level detection. A sensor network with robust, non-intrusive sensors such as CO2, temperature, relative humidity, and acoustics is deployed in an open-plan office space. Using information theory, the physical correlation between the number of occupants and various combination of features extracted from sensor data has been studied. The results show significant correlation between features extracted from humidity, acoustics, and CO2, while little correlation with temperature data. Using features from multiple sensors increases correlation further, and nearly 90% information gain is acquired when nine of the most informative features are combined.