Abstract
The growing elderly population living independently demands remote systems for health monitoring. Falls are considered recurring fatal events and therefore have become a global health problem. Fall detection systems based on WiFi radio frequency signals still have limitations due to the difficulty of differentiating the features of a fall from other similar activities. Additionally, the antenna orientation has not been taking into account as an influencing factor of classification performance. Therefore, we present in this paper an analysis of the classification performance in relation to the antenna orientation and the effects related to polarization and radiation pattern. Furthermore, the implementation of a device-free fall detection platform to collect empirical data on falls is shown. The platform measures the Doppler spectrum of a probe signal to extract the Doppler signatures generated by human movement and whose features can be used to identify falling events. The system explores two antenna polarization: horizontal and vertical. The accuracy reached by horizontal polarization is 92% with a false negative rate of 8%. Vertical polarization achieved 50% accuracy and false negatives rate.
Highlights
Improvement on quality of life has resulted in an increased life expectancy
This paper presents a systematic analysis of the effects of the antenna orientation in a fall detection system based on the Doppler signatures of WiFi signals
The results obtained by our platform allowed us to assess the impact of antenna polarization in the fall detection rate
Summary
Improvement on quality of life has resulted in an increased life expectancy. In 2019, the population over 65 years had a 3% growth compared to 1990. Much of this sector of society tend to live independently For this reason, it is necessary to provide systems for remote healthcare and monitoring. An innovative technique has emerged in the last years: device-free monitoring based on radio-frequency (RF) signals. An RF signal shows fluctuations at the receiver due to absorption and reflections by moving people wandering in the proximity of the transmitting and receiving antennas [7,8]. These fluctuations can be characterized to identify activities of daily living (ADL) or to detect important sporadic events, such as the presence of burglars or the occurrence of accidents. RF monitoring systems are noninvasive because users do not need to carry a sensor and they preserve user privacy since no image is recorded
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
