Individual Identification Using Radar-Measured Respiratory and Heartbeat Features

TL;DR

This paper introduces a radar-based method for individual identification using combined respiratory and heartbeat features, achieving high accuracy in experimental scenarios with a millimeter-wave radar system.

Contribution

It presents a novel approach combining respiratory and heartbeat features extracted via radar for accurate individual identification, with optimized feature and classifier selection.

Findings

Achieved 96.33% accuracy on a five-day dataset of six participants.

Achieved 99.39% accuracy on a public one-day dataset of thirty participants.

Demonstrated the effectiveness of combined respiratory and heartbeat features for identification.

Abstract

This study proposes a method for radar-based identification of individuals using a combination of their respiratory and heartbeat features. In the proposed method, the target individual's respiratory features are extracted using the modified raised-cosine-waveform model and their heartbeat features are extracted using the mel-frequency cepstral analysis technique. To identify a suitable combination of features and a classifier, we compare the performances of nine methods based on various combinations of three feature vectors with three classifiers. The accuracy of the proposed method in performing individual identification is evaluated using a 79-GHz millimeter-wave radar system with an antenna array in two experimental scenarios and we demonstrate the importance of use of the combination of the respiratory and heartbeat features in achieving accurate identification of individuals. The proposed method achieves accuracy of 96.33% when applied to a five-day dataset of six participants and 99.39% when applied to a public one-day dataset of thirty participants.