abstract

• Human fall detection has become one of the principal applications of smart healthcare. Several proposals based on sensors integrated into consumer electronic devices have been developed for fall detection. One of the most recent proposals is to employ radio signals of commercial WiFi devices as sensing probes. This radio sensing (RS) approach does not require wearing sensors and is viable for quick deployment due to the ubiquity of communication systems. However, the accuracy rate of WiFi-based fall detection systems is affected by several factors, such as the effects of thermal noise. In this article, we present the idea of a frequency-diversity enhanced RS system for human fall detection based on the analysis of Doppler signatures. We present an experimental proof of concept to validate the efficiency of this technique. For this, we use a deep learning model based on long-short-term memory networks. Our results have a significant improvement in the precision rate obtained with strategies that do not consider frequency diversity, increasing from 92.10%25 to 98.10%25.

authors

• Aguilar Ponce Ruth Mariela
• Gutiérrez Díaz De León Carlos Adrián

publication date

• 2024-01-01

funding provided via

• IF PROVIDED  Grant

published in

• IEEE Consumer Electronics Magazine  Journal

keywords

• Deep learning; Doppler effect; Fall detection; Feature extraction; Wi-Fi; Wireless local area networks (WLAN); Consumer electronic devices; Doppler frequency; Fall detection; Features extraction; Frequency diversity; Human fall detection; Radio sensing; Radio signals; Wi-Fi signals; Wireless fidelities; Probes

Digital Object Identifier (DOI)

• 10.1109/MCE.2023.3330302

PubMed ID

start page

• 75

end page

• 82

volume

• 13

issue

• 5