2-D Self-Injection-Locked Doppler Radar for Locating Multiple People and Monitoring Their Vital Signs

Su, Wei-Chih; Juan, Pin-Hsun; Chian, De-Ming; Horng, Tzyy‐Sheng; Wen, Chao-Kai; Wang, Fu-Kang

doi:10.1109/tmtt.2020.3037519

Cited by 23 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…People with COVID-19 usually experience fever and have difficulty in breathing that causes coughing with rapid and short breath (tachypnoea) [ 9 , 10 , 11 , 12 , 13 ]. Therefore, one of the critical conditions that needs to be monitored is the respiration pattern [ 14 , 15 , 16 , 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

Non-Contact Monitoring and Classification of Breathing Pattern for the Supervision of People Infected by COVID-19

Purnomo

Lin

Adiprabowo

et al. 2021

Sensors

View full text Add to dashboard Cite

During the pandemic of coronavirus disease-2019 (COVID-19), medical practitioners need non-contact devices to reduce the risk of spreading the virus. People with COVID-19 usually experience fever and have difficulty breathing. Unsupervised care to patients with respiratory problems will be the main reason for the rising death rate. Periodic linearly increasing frequency chirp, known as frequency-modulated continuous wave (FMCW), is one of the radar technologies with a low-power operation and high-resolution detection which can detect any tiny movement. In this study, we use FMCW to develop a non-contact medical device that monitors and classifies the breathing pattern in real time. Patients with a breathing disorder have an unusual breathing characteristic that cannot be represented using the breathing rate. Thus, we created an Xtreme Gradient Boosting (XGBoost) classification model and adopted Mel-frequency cepstral coefficient (MFCC) feature extraction to classify the breathing pattern behavior. XGBoost is an ensemble machine-learning technique with a fast execution time and good scalability for predictions. In this study, MFCC feature extraction assists machine learning in extracting the features of the breathing signal. Based on the results, the system obtained an acceptable accuracy. Thus, our proposed system could potentially be used to detect and monitor the presence of respiratory problems in patients with COVID-19, asthma, etc.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Contact Monitoring and Classification of Breathing Pattern for the Supervision of People Infected by COVID-19

Purnomo

Lin

Adiprabowo

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We assume as noise any source with a ratio less than 2. The latter comes with the observation that the respiratory physiology involves signals consisting of a dominant fundamental and smaller (more than half) harmonics 19 , 33 , 34 . In the two aforementioned situations, we set the SNR to the minimum of -20 dB.…”

Section: Methodsmentioning

confidence: 99%

“…Wang et al introduced the ViMo radar sensor for multi-person monitoring with a prior knowledge of the number of subjects 32 . Su et al presented the combination of a self-injection-locked (SIL) radar with FMCW and switched phased-array (SPA) techniques to locate multiple people 33 . Xiong et al proposed a SIMO CW radar and an adaptive digital beamforming technique to detect the respiration and angular information of multiple individuals 34 .…”

Section: Introductionmentioning

confidence: 99%

Automatic radar-based 2-D localization exploiting vital signs signatures

Mercuri

Russo

Glassée

et al. 2022

Sci Rep

View full text Add to dashboard Cite

In light of the continuously and rapidly growing senior and geriatric population, the research of new technologies enabling long-term remote patient monitoring plays an important role. For this purpose, we propose a single-input-multiple-output (SIMO) frequency-modulated continuous wave (FMCW) radar system and a signal processing technique to automatically detect the number and the 2-D position (azimuth and range information) of stationary people (seated/lying down). This is achieved by extracting the vital signs signatures of each single individual, separating the Doppler shifts caused by the cardiopulmonary activities from the unwanted reflected signals from static reflectors and multipaths. We then determine the number of human subjects present in the monitored environment by counting the number of extracted vital signs signatures while the 2-D localization is performed by measuring the distance from the radar where the vital signs information is sensed (i.e., locating the thoracic region). We reported maximum mean absolute errors (MAEs) of 0.1 m and 2.29$$^{\circ }$$ ∘ and maximum root-mean-square errors (RMSEs) of 0.12 m and 3.04$$^{\circ }$$ ∘ in measuring respectively the ranges and azimuth angles. The experimental validation demonstrated the ability of the proposed approach in monitoring paired human subjects in a typical office environment.

show abstract

“…They demonstrate feasibility of monitoring vital signs of up to three humans at a time. Su et al [41] then upgraded their approach by presenting a combination of a self-injection-locked radar with frequency-modulated continuous-wave and switched phased-array techniques used to locate multiple people and their vital signs with high resolution and sensitivity. This time they validated their approach by measuring locations and vitals of up to five seated persons at a range of more than 1.5 m. Some research stepped away from high-precision radars and rather focused on using cheaper omnipresent commodity devices, especially WiFi, in order to detect breathing.…”

Section: Rf-based Methodsmentioning

confidence: 99%

Classification of Hemodynamics Scenarios from a Public Radar Dataset Using a Deep Learning Approach

Slapničar

Wang

Luštrek

2021

Sensors

View full text Add to dashboard Cite

Contact-free sensors offer important advantages compared to traditional wearables. Radio-frequency sensors (e.g., radars) offer the means to monitor cardiorespiratory activity of people without compromising their privacy, however, only limited information can be obtained via movement, traditionally related to heart or breathing rate. We investigated whether five complex hemodynamics scenarios (resting, apnea simulation, Valsalva maneuver, tilt up and tilt down on a tilt table) can be classified directly from publicly available contact and radar input signals in an end-to-end deep learning approach. A series of robust k-fold cross-validation evaluation experiments were conducted in which neural network architectures and hyperparameters were optimized, and different data input modalities (contact, radar and fusion) and data types (time and frequency domain) were investigated. We achieved reasonably high accuracies of 88% for contact, 83% for radar and 88% for fusion of modalities. These results are valuable in showing large potential of radar sensing even for more complex scenarios going beyond just heart and breathing rate. Such contact-free sensing can be valuable for fast privacy-preserving hospital screenings and for cases where traditional werables are impossible to use.

show abstract

2-D Self-Injection-Locked Doppler Radar for Locating Multiple People and Monitoring Their Vital Signs

Cited by 23 publications

References 30 publications

Non-Contact Monitoring and Classification of Breathing Pattern for the Supervision of People Infected by COVID-19

Non-Contact Monitoring and Classification of Breathing Pattern for the Supervision of People Infected by COVID-19

Automatic radar-based 2-D localization exploiting vital signs signatures

Classification of Hemodynamics Scenarios from a Public Radar Dataset Using a Deep Learning Approach

Contact Info

Product

Resources

About