Bluetooth Low Energy Based Occupancy Detection for Emergency Management

Abstract

Abstract-A reliable estimation of an area's occupancy can be beneficial to a large variety of applications, and especially in relation to emergency management. For example, it can help detect areas of priority and assign emergency personnel in an efficient manner. However, occupancy detection can be a major challenge in indoor environments. A recent technology that can prove very useful in that respect is Bluetooth Low Energy (BLE), which is able to provide the location of a user using information from beacons installed in a building. Here, we evaluate BLE as the primary means of occupancy estimation in an indoor environment, using a prototype system composed of BLE beacons, a mobile application and a server. We employ three machine learning approaches (k-nearest neighbours, logistic regression and support vector machines) to determine the presence of occupants inside specific areas of an office space and we evaluate our approach in two independent experimental settings. Our experimental results indicate that combining BLE with machine learning is certainly promising as the basis for occupancy estimation.

Performance Evaluation of Bluetooth Low Energy: A Systematic Review

“…In this modality, different devices or sensors, provided with the BLE interface and placed in a structured environment, are programmed to send broadcast messages (described in Section 2.2.1 ) so that listener devices (e.g., user’s mobile device) can receive them. In this way, it is possible to send some pieces of information about the surrounding area [ 25 ], or to detect the user position [ 26 , 27 , 28 , 29 , 30 , 31 , 32 ], or to measure the distance between sensor devices in the environment [ 33 , 34 ], or also to detect the presence of devices, and so people [ 22 , 24 , 35 , 36 , 37 , 38 ]. Moreover, thanks to its versatility and low power consumption, BLE has also been applied in Internet of Things (IoT) technologies [ 39 ], for example transmitting Internet Protocol Version 6 (IPv6) packets over Low power Wireless Personal Area Networks [ 40 , 41 , 42 ] (6LowPAN) in health monitoring application [ 43 ].…”

Multi-User Low Intrusive Occupancy Detection

“…To review the performance of existing occupancy inference through BLE before doing fusion, we reproduce the work of Filippoupolitis et al [ 12 ] on our dataset. It is chosen due to its similarity to ours in terms of experimental setup and proposed technique (i.e., k -NN).…”

“…That is, several works have investigated occupancy status at a coarser granularity [ 11 ] or using a high number of power meters [ 6 ]. From the BLE perspective, several authors have used it for localization, e.g., [ 12 , 13 ]. Related works appear to have good portability, though we have a different aim, that is a richer contextual description such as multi-occupancy detection.…”

Intra-building People Localisation Using Personal Bluetooth Low Energy (BLE) Devices

“…Filippoupolitis et al [14] proposes and practically proves the approach that people localisation indoors is possible without the need of using any standard localisation processes in mobile phones. Instead of it, the data is sent to a remote server, where it is processed using calculations of the building occupancy using the classifier that has been initially trained during the data gathering phase.…”

“…The results of practical experiment show that utilising machine learning techniques in combination with BLE technology has a promising potential for accurate indoor localisation. Also the potential of this approach indicates that utilisation of it can contribute to changing emergency management to be more efficient, excluding one of the potentially vulnerable technique, which can fail in case of emergency, leading to the overall reliability and stability of the system [14].…”