Contactless person identification using cardiac radar signals

Radar systems have been researched for the use of presence detection and contactless vital sign monitoring. However, there exists no established biometrics for remote and unique person identification during such monitoring. Conventional biometrics like fingerprint or iris scan yield the disadvantage that direct contact with the person is needed. This paper explores the possibility of using cardiac radar signals as new biometric parameter for unique person identification. Measurements on different persons are performed using a 24 GHz continuous wave radar system which utilizes the Six-Port technology. An advanced signal processing and classification routine is presented to perform automatic person identification. Among several classifiers, quadratic support vector machines achieve the best performance and reach an overall accuracy of up to 94.6 %.

[1]  Wei Hu,et al.  Noncontact Accurate Measurement of Cardiopulmonary Activity Using a Compact Quadrature Doppler Radar Sensor , 2014, IEEE Transactions on Biomedical Engineering.

[2]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Muhammad Jawad Hussain,et al.  I Sense You by Breath: Speaker Recognition via Breath Biometrics , 2020, IEEE Transactions on Dependable and Secure Computing.

[4]  Jenshan Lin,et al.  Fast Acquisition of Heart Rate in Noncontact Vital Sign Radar Measurement Using Time-Window-Variation Technique , 2016, IEEE Transactions on Instrumentation and Measurement.

[5]  Dan Rissacher,et al.  Cardiac radar for biometric identification using nearest neighbour of continuous wavelet transform peaks , 2015, IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2015).

[6]  Robert Weigel,et al.  Local Pulse Wave Detection Using Continuous Wave Radar Systems , 2017, IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology.

[7]  Changzhi Li,et al.  A Review on Recent Advances in Doppler Radar Sensors for Noncontact Healthcare Monitoring , 2013, IEEE Transactions on Microwave Theory and Techniques.

[8]  Olga Boric-Lubecke,et al.  High dynamic range DC coupled CW Doppler radar for accurate respiration characterization and identification , 2017, 2017 89th ARFTG Microwave Measurement Conference (ARFTG).

[9]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[10]  Victor M. Lubecke,et al.  Noncontact Doppler radar unique identification system using neural network classifier on life signs , 2016, 2016 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems (BioWireleSS).

[11]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[12]  Patrizio Campisi,et al.  Visually evoked potential for EEG biometrics using convolutional neural network , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[13]  Robert Weigel,et al.  A low power 24 GHz radar system for occupancy monitoring , 2015, 2015 IEEE Radio and Wireless Symposium (RWS).

[14]  Alexander Koelpin,et al.  Six-Port Based Interferometry for Precise Radar and Sensing Applications , 2016, Sensors.

[15]  John Daugman,et al.  How iris recognition works , 2002, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  S. A. Khonsary.  Guyton and Hall: Textbook of Medical Physiology , 2017, Surgical Neurology International.

[17]  K. Holldack,et al.  Atlas und Kurzgefasstes Lehrbuch der Phonokardiographie und verwandter Untersuchungsmethoden , 1956 .

[18]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[19]  Isao Nakanishi,et al.  Biometric potential of brain waves evoked by invisible visual stimulation , 2017, 2017 International Conference on Biometrics and Kansei Engineering (ICBAKE).