Radar is an attractive approach for identity authentication because it requires no contact and is unobtrusive. Most reported results have focused only on sedentary breathing patterns, without considering how respiratory patterns may change due to physiological activities or emotional stress. In this research the feasibility of extracting identifying features from radar respiratory traces was tested, for sedentary subject conditions as well as just after performing physiological activities (walking upstairs). Respiratory breathing dynamics related features (breathing rate, spectral entropy, breathing depth, inhale/exhale area ratio, mean and standard deviation of the peaks) were extracted from radar captured respiration patterns, and variations in feature parameters after physiological activities were assessed. Experimental results demonstrated that, after short exertions dynamically segmented respiratory pattern exhale area and breathing depth increased by more than 1.4 times for all participants, which made evident the uniqueness of residual heart volume after expiration for recognizing each subject even after short exertions. Our proposed approach is also integrated with a Support Vector Machine (SVM) with a radial basis function kernel to demonstrate an identification success rate of almost 98.55% for sedentary-only conditions and almost 92% for a combined mixture of conditions (sedentary and after short exertion). While the efficacy was reduced,more »
This content will become publicly available on August 22, 2023
Identity Authentication in Two-Subject Environments Using Microwave Doppler Radar and Machine Learning Classifiers
Identity authentication based on Doppler radar respiration sensing is gaining attention as it requires neither contact nor line of sight and does not give rise to privacy concerns associated with video imaging. Prior research demonstrating the recognition of individuals has been limited to isolated single subject scenarios. When two equidistant subjects are present, identification is more challenging due to the interference of respiration motion patterns in the reflected radar signal. In this research, respiratory signature separation techniques are functionally combined with machine learning (ML) classifiers for reliable subject identity authentication. An improved version of the dynamic segmentation algorithm (peak search and triangulation) was proposed, which can extract distinguishable airflow profile-related features (exhale area, inhale area, inhale/exhale speed, and breathing depth) for medium-scale experiments of 20 different participants to examine the feasibility of extraction of an individual’s respiratory features from a combined mixture of motions for subjects. Independent component analysis with the joint approximation of diagonalization of eigenmatrices (ICA-JADE) algorithm was employed to isolate individual respiratory signatures from combined mixtures of breathing patterns. The extracted hyperfeature sets were then evaluated by integrating two different popular ML classifiers, k-nearest neighbor (KNN) and support vector machine (SVM), for subject authentication. Accuracies of 97.5% for two-subject experiments and 98.33% for single-subject experiments were achieved, which supersedes the performance of prior reported methods. The proposed identity authentication approach has several potential applications, including more »
- Publication Date:
- NSF-PAR ID:
- Journal Name:
- IEEE Transactions on Microwave Theory and Techniques
- Page Range or eLocation-ID:
- 1 to 14
- Sponsoring Org:
- National Science Foundation
More Like this
Extracting Individual Respiratory Signatures from Combined Multi-Subject Mixtures with Varied Breathing Pattern Using Independent Component Analysis with the JADE AlgorithmConcurrent respiration monitoring of multiple subjects remains a challenge in microwave Doppler radar-based non-contact physiological sensing technology. Prior research using Independent component analysis with the JADE algorithm has been limited to the separation of respiratory signatures for normal breathing patterns. This paper investigates the feasibility of using the ICA-JADE algorithm with a 24-GHz phase comparison monopulse radar transceiver for separating respiratory signatures from combined mixtures of varied breathing patterns. Normal, fast, and slow breathing pattern variations likely to occur due to physiological activity, and emotional stress were used as a basis for assessing separation robustness. Experimental results showed efficacy for recognition of three different breathing patterns, and isolation of respiratory signatures with an accuracy of100% for normal breathing, 92% for slow breathing, and 83.78% for fast breathing using ICA-JADE. Breathing pattern variations were observed to affect the signal-to-noise ratio through multiple mechanisms, decreasing with an increase in the number of breathing cycles and associated motion artifacts. Additionally, for removing motion artifacts of fast breathing pattern empirical mode decomposition (EMD) is employed, and for slow breathing pattern, increasing the breathing cycles helps to achieve an accuracy of 89.2% and 94.5% respectively.
Identity Authentication of OSA Patients Using Microwave Doppler radar and Machine Learning ClassifiersNon-contact home-based sleep monitoring will bring a paradigm shift to diagnosis and treatment of Obstructive Sleep Apnea (OSA) as it can facilitate easier access to specialized care in order to reach a much boarder set of patients. However, current remote unattended sleep studies are mostly contact sensor based and test results are sometimes falsified by sleep-critical job holders (driver, airline pilots) due to fear of potential job loss. In this work, we investigated identity authentication of patients with OSA symptoms based on extracting respiratory features (peak power spectral density, packing density and linear envelop error) from radar captured paradoxical breathing patterns in a small-scale clinical sleep study integrating three different machine learning classifiers (Support Vector Machine (SVM), K-nearest neighbor (KNN), Random forest). The proposed OSA-based authentication method was tested and validated for five OSA patients with 93.75% accuracy using KNN classifier which outperformed other classifiers.
Non-contact vital signs monitoring using microwave Doppler radar has shown great promise in healthcare applications. Recently, this unobtrusive form of physiological sensing has also been gaining attention for its potential for continuous identity authentication, which can reduce the vulnerability of traditional one-pass validation authentication systems. Physiological Doppler radar is an attractive approach for continuous identity authentication as it requires neither contact nor line-of-sight and does not give rise to privacy concerns associated with video imaging. This paper presents a review of recent advances in radar-based identity authentication systems. It includes an evaluation of the applicability of different research efforts in authentication using respiratory patterns and heart-based dynamics. It also identifies aspects of future research required to address remaining challenges in applying unobtrusive respiration-based or heart-based identity authentication to practical systems. With the advancement of machine learning and artificial intelligence, radar-based continuous authentication can grow to serve a wide range of valuable functions in society.
Comparative Analysis of Phase-Comparison Monopulse and MUSIC Algorithm Methods for Direction of Arrival (DOA) of Multiple-Subject Respiration Measured with Doppler RadarWhile Doppler radar measurement of respiration has shown promise for various healthcare applications, simultaneous sensing of respiration for multiple subjects in the radar field of view remains a significant challenge as reflections from the subjects are received as an interference pattern. Prior research has demonstrated the basic feasibility of using phase comparison with a 24-GHz Monopulse radar for isolation of one subject when another subject was in view, by estimating each subject's angular location with 88% accuracy. The integration of the high-resolution Multiple Signal Classification (MUSIC) algorithm with a phase-comparison technique is proposed to achieve robust accuracy for practical multi-subject respiration monitoring. Experimental results for this work demonstrate that the MUSIC pseudo-spectrum can separate two subjects 1.5 meters apart from each other at a distance of 3 meters from the sensor, using the same antenna array elements, spacing, and experimental scenarios previously reported for phase comparison Monopulse alone. Experimental results demonstrate that the MUSIC algorithm outperforms the phase-comparison technique with an azimuth angular position estimation accuracy over 95%. Higher accuracy indicates the system has improved robustness concerning noise and interference.