Radar sensing has emerged as a promising solution for the contactless monitoring of Heart Rate Variability (HRV), a crucial indicator of the cardiovascular and autonomic nervous systems. However, due to signal noise and interference that easily obscure heartbeat details, along with variations in heartbeat across different physiological conditions, existing methods remain restricted to laboratory settings with healthy subjects and fail in real-world scenarios involving more complex physiological conditions. In this study, we propose a physiological prior-inspired deep learning framework for robust radar-based HRV monitoring. Specifically, we leverage the prior that internal heartbeats drive movements across the entire torso surface and design a hybrid deep neural network to model the spatio-temporal relationship between full-body radio reflections and heartbeats, effectively mitigating interference. Then, we incorporate the cardiac motion's self-similarity prior to establish a signal augmentation strategy, effectively remodeling the HRV distribution and enhancing performance across diverse physiological conditions. We build and validate our method on a large-scale dataset comprising 7,150 outpatients with complex physiological conditions in real-world scenarios. The experimental results demonstrate that our method achieves a mean IBI error of 19.21 ms, an RMSSD error of 16.23 ms, an SDSD error of 16.70 ms, and a pNN50 error of 7.28%. We further validate the performance by classifying five common cardiac conditions based on HRV results, demonstrating performance comparable to ECG-based methods. These results highlight the great potential of our approach for accurate, contactless HRV monitoring in real-world applications.

Arrhythmias are prevalent cardiac disorders affecting millions worldwide. By analyzing cardiac motion modulated in mmWave reflections, mmWave sensing is emerging as a promising contactless revolution in arrhythmia detection compared to conventional contact-based methods. However, the fundamental bottleneck of existing mmWave sensing methods is their restriction to controlled laboratory settings with small-scale cohorts, limiting generalization to real-world populations. This limitation arises because mmWave signals undergo complex signal transformations during propagation, resulting in an explosion of signal diversity across large populations in real-world scenarios. Such diversity significantly complicates the direct recognition of arrhythmia. In this paper, we theoretically analyze the mechanism and impact of mmWave cardiac signal diversity. Leveraging the inherent transformation properties of mmWave signals, we propose a Diversity-Invariant Contrastive mmWave Sensing framework, which learns invariant features robust to complex signal transformations encountered in real-world scenarios. We evaluate our method in a practical, clinically-oriented scenario involving a large-scale population of 7,338 subjects, achieving an average F1-score of 0.8241 across four common arrhythmias. These results demonstrate that our method effectively bridges the diversity gap, representing a significant step toward practical clinical deployment of contactless arrhythmia detection via mmWave sensing.

Contactless stress monitoring, with its non-intrusive nature, is invaluable for maintaining mental and physical health. Recent studies have demonstrated encouraging results in contactless stress monitoring during daytime using radio frequency (RF) signals. However, the weak correlation between stress levels and behaviors during the night poses a significant challenge in stress monitoring, which remains unsolved. In this paper, we propose mmWave Nighttime Stress monitoring (mmNS), a learning-based end-to-end framework for contactless nighttime stress monitoring. Specifically, this framework incorporates radar signal processing and a self-supervised physiological feature separation strategy, combined with a signal complexity-oriented network design, to effectively extract and encode periodic physiological features for accurate stress level classification. To evaluate the stress monitoring performance of mmNS, we collect a RF-based nighttime stress monitoring dataset, which contains stress data from 10 volunteers. The experimental results demonstrate that our method achieves state-of-the-art stress monitoring performance, about 76% accuracy and 72% F1-score in classifying low, medium and high stress. To our knowledge, this is the first attempt dealing with contactless nighttime stress monitoring.

Radio sensing has emerged as a promising contactless revolution for cardiac monitoring. However, considering the complexity of radio propagation, extracting stable and clinically meaningful features remains challenging, posing a barrier to scaling this technology for practical and clinical reliable deployment. In this demo, we present RadioCardiogram, a system that leverages AI-powered knowledge transfer from well-established ECG diagnostic paradigms to accurately interpret complex radio signals. It enables all-in-one cardiac function monitoring including heart rate variability analysis, arrhythmia detection, and ECG-aligned waveform reconstruction. The system is implemented in a mobile phone-sized prototype and validated in a large-scale, clinically oriented cohort involving 6,258 outpatient visitors. Results demonstrate performance approaching the gold standard in both HRV monitoring and arrhythmia detection, highlighting a pathway toward effortless continuous, and reliable cardiac health coverage in real-world usage. The demo video is available at the following link.

By analyzing cardiac motion modulated in body reflections, radio signals offer a novel contactless pathway for heartbeat sensing, attracting growing research attention. However, current studies overlooked the unique signal interaction when radio signals are incident at non-normal directions to the torso surface. This missing component significantly limits the effectiveness and results in unreliable performance in practical usage, where normal sensing direction cannot always be guaranteed. In this paper, we aim to answer the questions of what causes this performance degradation and how to solve it. Specifically, we analyze the signal interaction using a fine-grained thoracic motion model and reveal that non-stationary interference, caused by physiologically-driven spatial variation of the body surface, is the key to the problem. Correspondingly, we propose OSense, a framework based on a time-domain optimization method to cancel the non-stationary interference. This framework can be seamlessly integrated into various heartbeat sensing tasks. We validate OSense using a commercial Frequency Modulated Continuous Wave radar across multiple downstream tasks. The results demonstrate that our method effectively eliminates interference and enables direction-robust heartbeat sensing, highlighting its potential for practical cardiac monitoring using radio signals.

Radio sensing has emerged as a promising solution for monitoring vital signs in a contactless manner. However, most of the existing designs focus on stationary target and struggle with body motion interference. While some efforts have been made to address this issue, the lack of a physical explanation for the motion elimination principle makes them work as a blind signal separation way and thus leaves the body motion elimination problem still as an open challenge. In this paper, we reveal for the first time the existence of “dark pixels”–specific points on the same rigid body parts that share the same body movement but exhibit varying physiological motions, with these variations still preserving the physiological rhythm. By exploiting the inherent relationship between the dark pixels, we propose a cooperative sensing framework, Co-Sense, that can achieve robust radio sensing for non-stationary targets in an explainable way. Through extensive experiments, Co-Sense demonstrates its superiority over existing methods, achieving effective motion cancellation and breath sensing with a median absolute respiratory rate (RR) error of 0.36 respiration per minute (RPM) and breath wave correlation of 0.61 under non-stationary scenarios. The results indicate the great potential of Co-Sense in enhancing the accuracy of vital sign sensing with radio signals, especially in real-world environments where targets are rarely stationary.

Millimeter-wave (mmWave) radar sensing powered by deep learning is now emerging in numerous applications, which are predominantly trained in a supervised manner. However, due to the non-interpretable nature of mmWave signals, labeling the radar data has always been a difficult task. While there have been investigations on unsupervised pre-training for mmWave radar sensing, these methods are tailored to specific signal representations. In this paper, we propose UMIMO, an unsupervised learning framework combining the hardware nature of MIMO radar and deep learning techniques to resolve the challenge raised by the insufficient labeled data. UMIMO leverages the antenna arrays synthesized from multiple transmitting and receiving antennas in mmWave radar to construct positive samples for contrastive learning. To achieve this, we propose the constraints on angular resolution and grating lobes to generate effective signal representations with different synthetic arrays. We conduct experiments using UMIMO on three tasks: contactless ECG monitoring, 3D human pose estimation, and human silhouette generation. All experimental results demonstrate that UMIMO can effectively improve the performance of learning-based mmWave radar sensing in an unsupervised manner.

Contactless vital signs estimation using mmWave radar has gained significant attention. However, existing studies are built upon the radar being directed facing the thorax to capture fine-grained vital signs, ignoring the angle variation between the radar and thorax in practical deployment. In this paper, we propose a spatial-temporal optimization model to estimate the human body orientations between the radar and thorax through extracting the multi-domain features of reflected signal. By aligning the signal variation captured from different angles, we can realize orientation-free vital sign sensing. The system achieves an average angle estimation error of 13.1°, and a 14.8% discrepancy reduction in terms of the mean absolute error of the signal captured at different angles.

Radar sensing has been a promising solution for contactless monitoring of Heart Rate Variability (HRV), an essential indicator of the cardiovascular and autonomic nervous systems. However, existing works neglect heartbeat-driven body surface motions spreading across the entire body with spatial variations, which limits their accuracy in identifying fine-grid consecutive heartbeat timings and overall HRV performance. In this paper, we propose to exploit the entire body reflections and model the inherent spatial-temporal relationship between these reflections and heartbeats by deep neural network for contactless HRV monitoring. Specifically, a hybrid convolution-transformer-based network is designed to convert the complex multi-dimensional spatial-temporal modeling problem into an efficient sequence modeling process. Experimental results demonstrate its superiority over the baseline method, achieving the median IBI estimation error of 12ms (w.r.t. 98.47% accuracy), RMSDD error of 7.3ms, SDRR error of 2.9ms, pNN50 error of 5.5%.

The mutual interference mitigation between identical or similar radar systems in autonomous driving has gained wide spread attention from both academia and industry. The resulted ghost target interference will reduce the sensitivity of the radar sensor and increase the false alarm rate. To tackle this problem, in this paper, we make full use of two characteristics of interference to achieve ghost target interference mitigation in the Doppler domain. The key insight lies in the fact that the interference is one-way propagation, and thus the resulted ghost target can be converted to the noise floor in the Doppler domain through random slow-time coding. Moreover, the high power characteristic of interference allows us to further enhance the interference mitigation performance by adopting a signal-to-interference-plus-noise ratio (SINR) maximization principle. Numerical examples are provided to demonstrate the effectiveness of the proposed interference mitigation approach.

The electrocardiogram (ECG) has always been an important biomedical test to diagnose cardiovascular diseases. Current approaches for ECG monitoring are based on body attached electrodes leading to uncomfortable user experience. Therefore, contactless ECG monitoring has drawn tremendous attention, which however remains unsolved. In fact, cardiac electrical-mechanical activities are coupling in a well-coordinated pattern. In this paper, we achieve contactless ECG monitoring by breaking the boundary between the cardiac mechanical and electrical activity. Specifically, we develop a millimeter-wave radar system to contactlessly measure cardiac mechanical activity and reconstruct ECG without any contact in. To measure the cardiac mechanical activity comprehensively, we propose a series of signal processing algorithms to extract 4D cardiac motions from radio frequency (RF) signals. Furthermore, we design a deep neural network to solve the cardiac related domain transformation problem and achieve end-to-end reconstruction mapping from RF input to the ECG output. The experimental results show that our contactless ECG measurements achieve timing accuracy of cardiac electrical events with median error below 14ms and morphology accuracy with median Pearson-Correlation of 90% and median Root-Mean-Square-Error of 0.081mv compared to the groudtruth ECG. These results indicate that the system enables the potential of contactless, continuous and accurate ECG monitoring.

The past decade has witnessed emerging applications of breath monitoring using off-the-shelf WiFi devices owing to their low-cost, non-intrusive, and privacy-friendly characteristics. While existing works have achieved promising results in certain scenarios, the performance degradation introduced by the interfering person who moves around the target user has not been fully investigated, which hinders practical applications of WiFi-based breath sensing. In this paper, we propose a robust respiration sensing system with WiFi which could achieve accurate respiration sensing under strong interference. To achieve this, we first design a 2-D Capon beamformer to maximize the signal-to-interference-plus-noise ratio (SINR). Then, the interfering user’s trajectory is estimated through spatial-temporal processing. Finally, we design a respiration extracting algorithm based on the constraint of the interferer’s trajectory and breath energy to find the optimal position to extract breath signals. Extensive experimental results show that the proposed framework can reduce the Mean Absolute Error (MAE) of breath rate estimation by up to 48% compared with the existing state-of-the-art methods, which demonstrates the superior robustness and effectiveness of our system.

The past years have witnessed increasing research interests in achieving passive human localization using WiFi signals. However, due to the limited spatial resolution of WiFi devices, it is still difficult to achieve accurate localization with existing WiFi infrastructures. To tackle this problem, in this paper, we propose a RIS-aided passive localization frame-work, which exploits the degree of freedom provided by the Reconfigurable Intelligent Surface (RIS) to achieve accurate localization. We have noted that RIS is composed of a large number of controllable reflective elements, which can break through the resolution limitation of commodity WiFi devices without making any changes to existing infrastructures. Hence, we propose a phase control optimization algorithm that can maximize the discrepancy between human reflection and multi-path interference. In order to solve the near-far effect in multi-person scenario, we propose a Side-lobe Cancellation Algorithm to separate the reflected signals of different people and achieve accurate localization. Extensive simulation results demonstrate the proposed framework is capable of locating the moving persons passively with sub-centimeter accuracy in the presence of noise and multi-path interference.

Human gesture recognition using millimeter-wave (mmWave) signals provides attractive applications including smart home and in-car interfaces. While existing works achieve promising performance under controlled settings, practical applications are still limited due to the need of intensive data collection, extra training efforts when adapting to new domains, and poor performance for real-time recognition. In this paper, we propose DI-Gesture, a domain-independent and real-time mmWave gesture recognition system. Specifically, we first derive signal variations corresponding to human gestures with spatial-temporal processing. To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework for mmWave signals based on correlations between signal patterns and gesture variations. Furthermore, a spatial-temporal gesture segmentation algorithm is employed for real-time recognition. Extensive experimental results show DI-Gesture achieves an average accuracy of 97.92%, 99.18%, and 98.76% for new users, environments, and locations, respectively. We also evaluate DI-Gesture in challenging scenarios like real-time recogntion and sensing at extreme angles, all of which demonstrates the superior robustness and effectiveness of our system.

Human silhouette segmentation, which is originally defined in computer vision, has achieved promising results for understanding human activities. However, the physical limitation makes existing systems based on optical cameras suffer from severe performance degradation under low illumination, smoke, and/or opaque obstruction conditions. To overcome such limitations, in this paper, we propose to utilize the radio signals, which can traverse obstacles and are unaffected by the lighting conditions to achieve silhouette segmentation. The proposed RFMask framework is composed of three modules. It first transforms RF signals captured by millimeter wave radar on two planes into spatial domain and suppress interference with the signal processing module. Then, it locates human reflections on RF frames and extract features from surrounding signals with human detection module. Finally, the extracted features from RF frames are aggregated with an attention based mask generation module. To verify our proposed framework, we collect a dataset containing804,760radio frames and402,380camera frames with human activities under various scenes. Experimental results show that the proposed framework can achieve impressive human silhouette segmentation even under the challenging scenarios (such as low light and occlusion scenarios) where traditional optical-camera-based methods fail. To the best of our knowledge, this is the first investigation towards segmenting human silhouette based on millimeter wave signals. We hope that our work can serve as a baseline and inspire further research that perform vision tasks with radio signals. The dataset and codes will be made in public.

The past years have witnessed increasing research interest in achieving passive human localization with commodity WiFi devices. However, due to the fundamental limited spatial resolution of WiFi signals, it is still very difficult to achieve accurate localization with existing commodity WiFi devices. To tackle this problem, in this paper, we propose to exploit the degree of freedom provided by the Intelligent Reflecting Surface (IRS), which is composed of a large number of controllable reflective elements, to modulate the spatial distribution of WiFi signals and thus break down the spatial resolution limitation of WiFi signals to achieve accurate localization. Specifically, in the single-person scenario, we derive the closed-form solution to optimally control the phase shift of the IRS elements. In the multi-person scenario, we propose a Side-lobe Cancellation Algorithm to eliminate the near-far effect to achieve accurate localization of multiple persons in an iterative manner. Extensive simulation results demonstrate that without any change to the existing WiFi infrastructure, the proposed framework can locate multiple moving persons passively with sub-centimeter accuracy under multipath interference and random noise.

Human gesture recognition using millimeter wave (mmWave) signals provides attractive applications including smart home and in-car interfaces. While existing works achieve promising performance under controlled settings, practical applications are still limited due to the need for intensive data collection, extra training efforts when adapting to new domains (i.e. environments, persons and locations) and poor performance for real-time recognition. In this paper, we propose DI-Gesture, a domain-independent and real-time mmWave gesture recognition system. Specifically, we first derive the signal variation corresponding to human gestures with spatial-temporal processing. To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework based on the correlation between signal patterns and gesture variations. Furthermore, we propose a dynamic window mechanism to perform gesture segmentation automatically and accurately, thus enabling real-time recognition. Finally, we build a lightweight neural network to extract spatial-temporal information from the data for gesture classification. Extensive experimental results show DI-Gesture achieves an average accuracy of 97.92%, 99.18% and 98.76% for new users, environments and locations, respectively. In real-time scenario, the accuracy of DI-Gesture reaches over 97% with an average inference time of 2.87ms, which demonstrates the superior robustness and effectiveness of our system.

The monitoring of blood pressure is critical for the prevention, diagnosis and treatment of cardiovascular diseases. However, existing methods require physical contact between human body and sensor, which are not suitable for long-term monitoring. In this paper, we propose a contactless blood pressure monitoring system, mmBP, using millimeter wave radar. Specifically, we first separate signals reflected from different spatial locations by coherently combining the signals on different antennas. Then, we locate and extract the arterial pulse using convolutional neural network (CNN) assisted template matching with location tracking. Finally, we design an encoder-decoder neural network to derive the blood pressure information from the extracted signal. Experimental results on 20 subjects show that the measurement deviation rate is 9.00% and 3.69% for systolic and diastolic blood pressure, which demonstrates the feasibility and effectiveness of the proposed system.

Fall is a severe health threat for elders’ health care. While existing systems could achieve promising performance under specific scenarios, the required computing resources are usually not affordable, which is not applicable for real-time detection. In this paper, we propose mmFall, a real time fall detection system using millimeter wave signal which can achieve impressive accuracy with low computation complexity. Specifically, we first extract the signal variation corresponding to human activity with spatial-temporal processing. To enhance the system performance and robustness, we perform data augmentation by shifting, flipping, extracting and interpolating the signal. Finally, we design a light-weight convolutional neural network to achieve real-time fall detection. Extensive experimental results demonstrate that the pro-posed system could achieve state-of-the-art performance with limited computation complexity.

By leveraging the mechanical motions on the body surface conducted by physiological activities, many works have achieved radio-frequency(RF)-based physiological sensing. However, previous works generally simplify the model on both the mechanism of physiological motion and the signal propagation around the human body, which leads to the loss of valuable information. In this paper, we introduce the concept of micro-motion(MM) camera to provide a more cognitive imaging modality to observe torso surface motion comprehensively so as to dynamically image the motions of the breath and cardiac activities. We develop a sub-6G MMCamera prototype system. The camera functionality is implemented to prove the concept novelty from the view of respiratory-cardiovascular system monitoring. Our result shows that the proposed system could provide fine-grid torso surface motion imaging with breath and cardiac activities distributed over the entire thorax and abdomen.

Vibration is a widespread physical phenomenon that often carries important information such as the internal state of the devices. Thus, vibration measurement is of great importance in the field of modern engineering and has drawn much attention. While achieving promising performance, existing methods fail when the vibration amplitude is tiny, e.g, smaller than 50 um. To address such a challenge, in this paper, we propose a contactless method with deep learning, denoted as DeepVib, to sense the tiny vibration using millimeter wave radar. Specifically, DeepVib first makes full advantage of the physical characteristics of the vibrating object and combines Range-Doppler FFT to find the range bin of vibrating objects. Then, DeepVib trains a denoising neural network using a large amount of simulated data, which takes the noisy sample points as input and outputs the denoised data with better SNR. Finally, the vibration status is recovered through the phase variation of the extracted signal. Simulation results show that DeepVib achieves over 40% improvement in measuring um-level amplitudes with over 5x faster processing time, while real experimental results show that DeepVib achieves a mean amplitude error of 2.1 um for the 100um-amplitude vibration.