Summary
International Conference on Emerging Technologies for Communications
2022
Session Number:S12
Session:
Number:S12-8
Deep Learning-based Person Identification using Vital Signs Extracted from Radar Signal
ZELIN XING, Mondher Bouazizi, Tomoaki Ohtsuki,
pp.-
Publication Date:2022/11/29
Online ISSN:2188-5079
Summary:
The individuality of respiration has been discovered for a long time. With the development of radar systems, continuous wave Doppler radar is able to accurately detect the breathing of human. Some previous work shows that manually extracted respiration features combined with conventional machine learning classifiers can achieve high accuracy in person identification. To advance this study even further, we propose a deep learning-based person identification algorithm using Doppler radar-extracted human respiration signal. Compared with previous works, our method does not require extracting features manually. Implemented and tested on a dataset with 10 subjects, our proposed method reaches a high accuracy of 96.5%.