Abstract
Wireless sensing can enable human identification by quantifying individual behavior effects on wireless signal propagation. This work proposes a novel device-free biometric system, WirelessID, that explores the human fine-grained behavior and body physical signatures embedded in channel state information by extracting spatiotemporal features. In addition, the signal fluctuations corresponding to different parts of the body contribute differently to identification performance. Thus, to extract robust features, we introduce an attention mechanism into our system. Particularly, commercial Wi-Fi devices are used for prototyping WirelessID in a laboratory with an average accuracy of 93.14% and a best accuracy of 97.72% for five individuals.
Sign-in/Register to access full text options 
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
