FMCW-based contactless heart rate monitoring

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 21, 2025

Heart disease is a significant global health issue. Traditional methods for heart rate monitoring typically require close physical contact, which limits the continuity and convenience of monitoring. To achieve real-time, non-contact heartbeat monitoring, researchers have introduced millimeter-wave radar technology. The technology's penetration privacy offer potential solution condition Therefore, this study utilized frequency-modulated continuous wave (FMCW) Firstly, collected signals were preprocessed to accurately locate area cardiac activity in human body. Secondly, an adaptive variational mode decomposition (A-VMD) algorithm was designed extract signal, considering signal variations caused by random body movements respiration their harmonics, obtain accurate signal. Finally, obtained weighted estimation based on harmonic relationship invited ten subjects participate experiment verify effectiveness method. results show that method can reduce influence harmonics average absolute error less than four bpm.

Language: Английский

---

Radar-Based Human Activity Recognition: A Study on Cross-Environment Robustness

Electronics, Journal Year: 2025, Volume and Issue: 14(5), P. 875 - 875

Published: Feb. 23, 2025

Indoor radar-based human activity recognition (HAR) using machine learning has shown promising results. However, deploying an HAR model in unseen environments remains challenging due to a potential mismatch between training and operational conditions. Such can be reduced by acquiring annotated data more diverse situations. since this is time intensive, paper explores the application of augmentation unsupervised domain adaptation (UDA) enhance robustness models, even when they are trained very limited amount data. In initial analysis, baseline was evaluated validation set (a) from same environment as (b) different environment. The results showed 29.6% decrease F1-score tested on Implementing techniques—specifically, time–frequency warping—reduced performance gap 17.8%. Further improvements were achieved applying strategy, which brought drop down 13.2%. Furthermore, ablation study examining various methods synthetic sample quantities demonstrates superior our proposed approach. concludes with discussion how environmental variations, such changes aspect angle, occlusion layout, affect time-Doppler radar representation and, consequently, performance.

Language: Английский

---

Driver Head–Hand Cooperative Action Recognition Based on FMCW Millimeter-Wave Radar and Deep Learning

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2399 - 2399

Published: April 10, 2025

Driver status plays a critical role in ensuring driving safety. However, the current visual recognition-based methods for detecting driver actions and are often limited to factors such as ambient light condition, occlusion, privacy concerns. In contrast, millimeter-wave radar offers various advantages high accuracy, ease of integration, insensitivity low cost; therefore, it has been widely used monitoring vital signals action recognition. Despite this, existing studies on recognition have hindered by accuracy narrow range detectable actions. this study, we utilized 77 GHz frequency-modulated continuous-wave construct dataset encompassing seven types head–hand cooperative Furthermore, deep learning network model based VGG16-LSTM-CBAM using micro-Doppler spectrograms input was developed classification. The experimental results demonstrated that, compared CNN-LSTM ALEXNET-LSTM networks, proposed achieves classification 99.16%, effectively improving detection.

Language: Английский

---

Radar-based Contactless Heart Beat Detection with a Modified Pan–Tompkins Algorithm

Biomedical Physics & Engineering Express, Journal Year: 2024, Volume and Issue: 11(1), P. 015007 - 015007

Published: Oct. 29, 2024

Abstract Background. Using radar for non-contact measuring human vital signs has garnered significant attention due to its undeniable benefits. However, achieving reasonably good accuracy in contactless measurement senarios is still a technical challenge. Materials and methods. The proposed method includes two stages. first stage involves the process of datasegmentation signal channel selection. In next phase, raw from chosen subjected modified Pan-Tompkins. Results. experimental findings twelve individuals demonstrated strong agreement between contact electrocardiography (ECG) devices heart rate measurement, with correlation coefficient 98.74 percentage; 95% limits obtained by those ECG were 2.4 beats per minute. Conclusion. results showed high calculated signals electrocardiograph. This research paves way future applications using sensors support potentially replace healthcare.

Language: Английский

---

Radar-Based Heart Cardiac Activity Measurements: A Review

Sensors, Journal Year: 2024, Volume and Issue: 24(23), P. 7654 - 7654

Published: Nov. 29, 2024

In recent years, with the increased interest in smart home technology and need to remotely monitor patients due pandemic, demand for contactless systems vital sign measurements has also been on rise. One of these kinds are Doppler radar systems. Their design is composed several choices that could possibly have a significant impact their overall performance, more specifically those focused measurement cardiac activity. This review, conducted using works obtained from relevant scientific databases, aims understand performance measuring either heart rate (HR) or variability (HRV). To end, an analysis based hardware architecture, carrier frequency, distance was focusing both aforementioned parameters, signal processing trends were discussed. What found system architecture algorithms had most FMCW being best performing whereas factors like frequency did not impact.This means newer can focus cheaper, lower-frequency without any degradation, which will make research easier.

Language: Английский

---