Tag-Fall: A Doppler Shift-Based Fall Detection Method Using RFID Passive Tags

As the global population ages, the prevalence of elderly individuals living independently has risen. As one of the main threats to the health of the elderly, falling seriously reduces the happiness of the elderly and imposes a burden on the medical system. Therefore, the exploration of automatic fall detection systems is crucial. However, proposed fall detection systems exhibit varying degrees of shortcomings. In this paper, we propose a new fall detection method utilizing Doppler shift with RFID passive tags. The motion of the passive tag induces a Doppler shift in the reflected signal. This method is the first to use Doppler frequency shift for fall detection in RFID. Additionally, a velocity-position iteration algorithm is applied to ascertain the tag's position and velocity over time. The combination of velocity and position for fall detection yields higher accuracy compared to individual parameters. The proposed method demonstrates the capability to differentiate between sudden and soft falls, aiding medical professionals in identifying the cause of a user's fall. The experimental results demonstrate that the system achieves an accuracy rate of 91.7% in detecting sudden falls, and this accuracy remains at 86.8% even after incorporating soft falls into the analysis. Consequently, the proposed method proves to be an effective and reliable approach for fall detection.