This study introduces a contactless blood pressure monitoring approach that combines conventional radar signal processing with novel deep learning architectures. During the preprocessing phase, datasets suitable for synchronization are created by integrating Kalman filtering, multiscale bandpass filters, and a periodic extraction method in the time domain. These data comprise data on chest micro variations, encapsulating a complex array of physiological and biomedical information reflective of cardiac micromotions. The Radar-based Stacked Deformable convolution Network (RSD-Net) integrates channel and spatial self attention mechanisms within a deformable convolutional framework to enhance feature extraction from radar signals. The network architecture systematically employs deformable convolutions for initial deep feature extraction from individual signals. Subsequently, continuous blood pressure estimation is conducted using self attention mechanisms on feature map from single source coupled with multi-feature map channel attention. The performance of model is corroborated via the open-source dataset procured using a non-invasive 24GHz six-port continuous wave radar system. The dataset, encompassing readings from 30 healthy individuals subjected to diverse conditions including rest, the Valsalva maneuver, apnea, and tilt-table examinations. It serves to substantiate the validity and resilience of the proposed method in the non-contact assessment of continuous blood pressure. Evaluation metrics reveal Pearson correlation coefficients of 0.838 for systolic and 0.797 for diastolic blood pressure predictions. The Mean Error (ME) and Standard Deviation (SD) for systolic and diastolic blood pressure measurements are -0.32 $\pm$ 6.14mmHg and -0.20 $\pm$ 5.50mmHg, respectively. The ablation study assesses the contribution of different structural components of the RSD-Net, validating their significance in the overall of model performance.

This paper proposes a real-time heart rate detection method based on 77 GHz FMCW radar. Firstly, the method establishes a new motion model according to respiratory and heartbeat rules, and extracts the motion signals of the chest and the abdomen; then, the random body motion (RBM) signal is eliminated by a combination of polynomial fitting and recursive least squares (RLS) adaptive filtering; lastly, multi-detection-point adaptive harmonics cancellation (AHC) is used to eliminate respiratory harmonics. In addition, the method introduces a spectrum analysis algorithm based on linear predictive coding (LPC). The experimental results show that the method can effectively eliminate the RBM signal and respiratory harmonics, and that the average real-time heart rate detection error rate is 2.925%.

Human activity recognition (HAR) based on radar has garnered wide interest due to its privacy-friendly and lighting-independent nature. Despite advancements, challenges like response speed and real-world applicability persist. To address these issues, data from different orientations utilizing frequency-modulated continuous-wave (FMCW) radar was collected to better reflect real-world conditions. In terms of data preprocessing, a sliding time-window non-local means filter is proposed to effectively remove the noise while retaining the micro-Doppler features. Subsequently, a multi-attention enhanced fusion network (MAEF-Net) is proposed for HAR. MAEF-Net, an efficient and lightweight architecture, integrates multiple attention mechanisms to enhance robustness in omnidirectional HAR. It achieves high-accuracy omnidirectional activity recognition by simultaneously focusing on local and global features. Experimental results showcase MAEF-Net achieving 98.3% accuracy in testing, surpassing existing methods, thereby demonstrating its effectiveness in real-world scenarios.

This article proposes a human pose recognition (HPR) system based on millimeter-wave (mmWave) radar (mRadHPRS). It includes an adaptive method for generating 3D point clouds of human bodies, a data augmentation method for sparse point clouds, and an HPR network based on mmWave radar (mmRadHPR). This study seeks to address a deficiency in current HPR research, which predominantly emphasizes various deep learning variants and often pays less attention to the accurate extraction of features from radar signals. The proposed system considers factors such as multipath effects in radar echoes and designs data augmentation methods tailored to the sparse distribution characteristics of mmWave radar point clouds. Additionally, a hierarchical point cloud processing network incorporating cross- and self-attention mechanisms is devised to extract human pose features. To evaluate the performance of the proposed model, we constructed a dataset with 10 different postures using mmWave radar. Experimental results demonstrate that the overall accuracy and average classification accuracy achieved by our method are 88.38% and 88.63%, respectively, significantly outperforming the three baseline methods. The system robustness experiment further validates the generalization ability and effectiveness of our approach.

In response to challenges posed by abnormal interference, such as target sidelobes within the reference window, this paper proposes a Sidelobe Suppression-Constant False Alarm Rate (SS-CFAR) detector. Drawing on the CLEAN concept, the SS-CFAR is designed for target detection in indoor environments with multiple targets using millimeter-wave radar. It employs second-order difference statistics combined with the Monte Carlo algorithm and iterative censoring to separate target signals from background clutter in radar echoes. Additionally, sidelobe suppression for the target is achieved by reconstructing the target’s echo information and the CLEAN concept. The simulation and actual experimental results demonstrate that SS-CFAR delivers superior detection performance, obviating the need for prior knowledge of anomalies or manual setting of parameters like the number of reference and guard cells, which traditionally depend on experiential adjustments. Compared to mean class and ordered statistics class CFAR detectors, SS-CFAR transcends reference window constraints. It accurately estimates background clutter, enhancing detection capabilities in multi-target environments. This innovative approach not only showcases superior detection performance and adaptability but also paves the way for the broader application of millimeter-wave radar in complex indoor scenarios.