Noncontact Doppler radar unique identification system using neural network classifier on life signs

Abstract

A continuous-wave (CW) Doppler radar-based unique-identification system has been studied. Experiments have been performed using a neural network based classifier to uniquely identify individuals based on the variation in their breathing energy, frequency and patterns captured by the radar. Our work shows the possibility of non-contact unique identification where camera based system is not preferred. It is demonstrated that the system is capable of identifying individuals with more than 90% accuracy. This study also has impact on radar-based breathing pattern classification for health diagnostics.