More Like this

1. Extracting Individual Respiratory Signatures from Combined Multi-Subject Mixtures with Varied Breathing Pattern Using Independent Component Analysis with the JADE Algorithm

   https://doi.org/10.1109/APMC47863.2020.9331715  

   Islam, Shekh M. ; Lubecke, Victor M. ( December 2020 , 2020 IEEE Asia-Pacific Microwave Conference (APMC))

   null (Ed.)

   Concurrent 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. 

   more » « less
2. An Adaptive Filter Technique for Platform Motion Compensation in Unmanned Aerial Vehicle Based Remote Life Sensing Radar

   https://doi.org/10.23919/EuMC48046.2021.9338011  

   Islam, Shekh M. ; Lubecke, Lana C. ; Grado, Christian ; Lubecke, Victor M. ( January 2021 , 2020 50th European Microwave Conference (EuMC))

   null (Ed.)

   Unmanned Aerial Vehicles (UAVs) have demonstrated efficacy as a platform for remote life sensing in post-disaster search and rescue applications. Radar-assisted UAV respiration motion sensing technology also shows promise yet a significant technological challenge remains associated with interfering motion artefacts from the moving UAV platform. The feasibility of integrating an adaptive filter approach for the compensation of platform motion artefacts is investigated here for the extraction of respiratory motion signatures. A 24-GHz dual radar system was attached to a mechanical mover to emulating motion artefacts while measuring the motion of a robotic breathing phantom designed to reproduce breathing motion patterns. Recursive least square (RLS) and a least mean square (LMS) adaptive filter algorithms were employed to test efficacy for extracting respiratory rate from the motion corrupted breathing signal. Experimental results demonstrated that the RLS performed best with an accuracy of 98.24% for extracting the frequency of the robotic breathing phantom mover. The proposed system has several potential applications including military, humanitarian, and post-disaster search and rescue operations. 

   more » « less
3. Identity Authentication in Two-Subject Environments Using Microwave Doppler Radar and Machine Learning Classifiers

   https://doi.org/10.1109/TMTT.2022.3197413  

   Islam, Shekh M. ; Boric-Lubecke, Olga ; Lubecke, Victor M. ( August 2022 , IEEE Transactions on Microwave Theory and Techniques)

   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 security/surveillance, the Internet-of- Things (IoT) applications, virtual reality, and health monitoring. 

   more » « less
4. A Chest‐Laminated Ultrathin and Stretchable E‐Tattoo for the Measurement of Electrocardiogram, Seismocardiogram, and Cardiac Time Intervals

   https://doi.org/10.1002/advs.201900290  

   Ha, Taewoo ; Tran, Jason ; Liu, Siyi ; Jang, Hongwoo ; Jeong, Hyoyoung ; Mitbander, Ruchika ; Huh, Heeyong ; Qiu, Yitao ; Duong, Jason ; Wang, Rebecca L. ; et al ( May 2019 , Advanced Science)

   Seismocardiography (SCG) is a measure of chest vibration associated with heartbeats. While skin soft electronic tattoos (e‐tattoos) have been widely reported for electrocardiogram (ECG) sensing, wearable SCG sensors are still based on either rigid accelerometers or non‐stretchable piezoelectric membranes. This work reports an ultrathin and stretchable SCG sensing e‐tattoo based on the filamentary serpentine mesh of 28‐µm‐thick piezoelectric polymer, polyvinylidene fluoride (PVDF). 3D digital image correlation (DIC) is used to map chest vibration to identify the best location to mount the e‐tattoo and to investigate the effects of substrate stiffness. As piezoelectric sensors easily suffer from motion artifacts, motion artifacts are effectively reduced by performing subtraction between a pair of identical SCG tattoos placed adjacent to each other. Integrating the soft SCG sensor with a pair of soft gold electrodes on a single e‐tattoo platform forms a soft electro‐mechano‐acoustic cardiovascular (EMAC) sensing tattoo, which can perform synchronous ECG and SCG measurements and extract various cardiac time intervals including systolic time interval (STI). Using the EMAC tattoo, strong correlations between STI and the systolic/diastolic blood pressures, are found, which may provide a simple way to estimate blood pressure continuously and noninvasively using one chest‐mounted e‐tattoo.

    

   more » « less
5. Cardiopulmonary Effective Radar Cross Section (ERCS) for Orientation of Sedentary Subject Using Microwave Doppler Radar

   https://doi.org/10.1109/APMC47863.2020.9331705  

   Snigdha, Farjana ; Ishmael, Khaldoon ; Neville, Ryan ; Boric-Lubecke, Olga ( December 2020 , 2020 IEEE Asia-Pacific Microwave Conference (APMC))

   null (Ed.)

   Effective radar cross-section (ERCS) for microwave Doppler radar, is defined by the reflected power from sections of the human body that undergo physiological motion. This paper investigates ERCS for human cardiopulmonary motion of sedentary subjects at three different positions (front, back and side with respect to radar). While human breathing and heartbeat can be measured from all four sides of the body, the characteristics of measured signals will vary with body orientation. Thus, continuous wave radar with quadrature architecture at 2. 4GHz was used to test a sedentary subject for three minutes from three different orientations: front, back and side with respect to radar. The results obtained from the tests showed that physiological motion could be obtained and that distinct patterns emerge due to the differences in the ERCS for each orientation. For the seated subject, back ERCS was higher than for front and side positions. Determining ERCS changes with position may enable determining body orientation with respect to the radar. This research opens further opportunities for development of high-resolution occupancy sensing and emergency search and rescue sensing, where the orientation of a human subject may be unknown ahead of time. 

   more » « less