Estimating Indoor Occupancy Through Low-Cost BLE Devices

Detecting the presence of persons and estimating their quantity in an indoor environment has grown importance recently. For example, information if a room is unoccupied can be used for automatically switching off light, air conditioning, ventilation, thereby saving significant amounts energy public buildings. Most existing solutions rely on dedicated hardware installations, which involve sensors, video cameras, carbon dioxide sensors. Unfortunately, such approaches are costly, subject to privacy concerns, have high computational requirements, lack ubiquitousness. The work presented this article addresses these limitations by proposing low-cost occupancy detection system. Our approach builds upon detecting variations Bluetooth Low Energy (BLE) signals related humans. effectiveness evaluated performing comprehensive tests five different datasets. We apply several pattern recognition models compare our methodology with systems building IEEE 802.11 (WiFi). On average, multifarious environments, we correctly classify accuracy 97.97%. When number people room, estimated subjects differs from actual one 0.32 persons. conclude that system's performance comparable ones based WiFi, while significantly reducing cost installation effort. Hence, makes practical real-world deployments.