B-FD: Indoor Fall Detection System Based On Bluetooth AOA
Qing Wan, Zeyun Liu, Yuxi Wang, Yuanhong Huang, Jinlin Yu, Jianghua Liu · IEEE Sensors Journal · 2025
China has now entered a moderately aging society. With the everaccelerating process of population ageing, more and more elderly people are living alone. And accidents such as falls among the elderly continue to occur, requiring a low-cost indoor fall detection system. The system is able to detect the occurrence of elderly falls and determine the location of the fall in order to notify the rescue in a timely manner. Currently, the most common method of indoor fall detection is to use cameras for monitoring, but this method will face the problem of invasion of privacy. To address this situation, this paper proposes a fall detection system called B-FD. The system is based on low-power Bluetooth Angle of Arrival (AOA) technology, which uses a Bluetooth AOA base station to collect In-phase Quadrature(IQ) values from Bluetooth beacon transmissions. It then uses machine learning techniques to categorise six common indoor postures to determine whether a fall has occurred. It can achieve an average detection accuracy of 98.14% for fall. The system can also accurately track the user’s movement and determine the exact location of the fall when it occurs. The Bluetooth beacon in the system is worn on the user’s arm and only needs to send low-power Bluetooth 5.1 broadcasts, which consume less power.The beacon does not require frequent recharging and is easy to wear for long periods of time. As a result, this monitoring system has a wide range of applications.