Yuan Wu

Effective heating, ventilation, and air conditioning (HVAC) systems are increasingly vital for public health, safeguarding indoor air quality and occupant safety across residential, occupational, and educational settings. Accurate, real-time monitoring of airflow speed is essential for optimizing HVAC performance and ensuring healthy environments. However, existing solutions face significant limitations: traditional anemometers are intrusive and incur high deployment costs, acoustic methods raise severe privacy concerns and are highly susceptible to environmental noise, and contact-based vibration sensors struggle to isolate blade micro-vibrations from overwhelming chassis noise. Millimeter-wave (mmWave) radar emerges as a compelling alternative, offering non-contact, privacy-preserving, and noise-robust sensing. Furthermore, it significantly reduces the Total Cost of Ownership (TCO) by multiplexing existing smart building sensors for a zero-marginal-cost deployment. Yet, the core challenge of reliably distinguishing and extracting fan blade micro-vibrations from dominant structural vibrations using commodity mmWave radar in noisy HVAC environments remains largely unaddressed. Motivated by this gap and the potential of mmWave sensing, we propose mmVibFlow, a mmWave radar-based method for airflow speed estimation by capturing the micro-vibrations of fan blades. mmVibFlow identifies the operating gear (speed level) of an air conditioner and predicts real-time airflow speed from the machine’s vibrations. To effectively distinguish mechanical chassis vibrations from the target fan blade micro-vibrations, we develop an interference-resistant vibration sensing framework. This framework first utilizes beamforming to decorrelate vibrations from the blade region and the chassis, then employs phase-based subtraction to isolate the fan blade vibrations. To extract informative features for airflow speed estimation from RF signals, we develop a signal representation method that captures multi-domain frequency features at different airflow speeds. We validate mmVibFlow, achieving 99% accuracy in gear classification and a mean squared error (MSE) of 0.05 in airflow speed estimation when the radar is placed within 1.5 meters of the air conditioner outlet. Experimental results demonstrate that mmVibFlow accurately measures airflow speed in real-world environments.

Ensuring operational safety in distribution rooms necessitates real-time tracking of electricians, yet conventional approaches face significant limitations in such challenging environments. Global Positioning System (GPS) technologies fail due to signal obstruction from dense cabinets and reinforced walls. While video-based systems suffer from occlusion-related inaccuracies, wearable sensors introduce usability constraints. In response, we introduce BodySensor—a non-contact, real-time positioning system that employs a single commercial off-the-shelf (COTS) ultra-wideband (UWB) radar to achieve fine-grained indoor tracking. Our framework incorporates a lightweight vision transformer architecture, termed Convolutional Patch Embedding Global Cross-attention Vision Transformer (CPE-GCrossViT), which combines convolutional patch embedding with global cross-attention to detect human presence from nonlinear multipath reflections. To further refine localization, we develop a multipath-weighted high-dimensional vector mapping approach that utilizes energy and range profiles of all multipath components for spectral matching-based position estimation. Extensive evaluations across three different settings, involving more than 30 hours of collected data, show that BodySensor reaches a coarse localization accuracy of 98.08%, with mean tracking errors of 6.2 cm in line-of-sight (LOS) and 10.9 cm under full NLOS conditions. The system performs consistently regardless of movement state, highlighting its operational robustness. BodySensor underscores the practical potential of radar-based sensing in smart grid applications, offering an unobtrusive and reliable means to improve personnel safety and operational efficiency.

Leather is among the most widely traded textile materials worldwide, and detecting surface defects is crucial to ensure its quality. The conventional manual inspection of leather surfaces is labor-intensive, time-consuming, and prone to human error. Advances in computer vision have facilitated the development of automated leather surface defect detection. However, vision-based methods remain sensitive to lighting conditions, particularly on high-gloss leather surfaces. In this article, we introduce Le-Radio, an Industrial Internet of Things (IIoT) oriented RF-based system for automated leather defect detection. Le-Radio provides a gloss-robust, ubiquitous, and continuous inspection solution, which is crucial for integrating quality control into smart factory pipelines and advancing the digital transformation of the traditional leather industry. To extract informative representations of leather defects from wireless signals, we employ continuous radio snapshots (CRSs) and refined signal features to differentiate defect patterns. Specifically, we design an imaging algorithm that continuously visualizes defects on moving leather samples using a fixed radar. To enhance Le-Radio’s robustness in diverse environments, we train a transferable model that maintains consistent detection performance across different scenarios. We conduct extensive experiments in three rooms using 120 leather samples to evaluate Le-Radio. Experimental results demonstrate that Le-Radio accurately detects diverse defects in high-gloss leather. Beyond leather inspection, this work establishes Le-Radio as a practical IoT edge sensing node for material surface inspection in the IIoT. By integrating RF-based defect scanning capabilities and a robust radar imaging framework into a unified system, this work establishes RF sensing as a viable and novel paradigm for material surface inspection in the IIoT, particularly in scenarios where optical methods are fundamentally limited.

Sitting posture is closely related to our health. Poor sitting posture can cause various diseases and jeopardize our health. Among the current methods for detecting sitting posture, computer vision solutions suffer from privacy leakage and wearable sensor solutions suffer from inconvenience and cost of wearing. In this study, we introduce 3D-Sitpose, which leverages millimeter-wave radar to detect human sitting posture. 3D-Sitpose utilizes wireless signal transmission for non-contact detection, ensuring privacy protection and cost reduction. Firstly, we analyze the impact of variations in human sitting posture on millimeter-wave radar signals, and design sophisticated signal processing methods to refine the collected radar data, yielding clearer point cloud information for volunteers in various sitting postures. Secondly, we develop a two-channel neural network to extract fine-grained features related to volunteers from the point cloud data. Finally, we obtain coordinates for 25 human skeletal points. 3D-Sitpose can instruct users to maintain correct sitting posture based on a set of six key angles. We recruit 20 volunteers from our institute to conduct comprehensive evaluations of 3D-Sitpose. Experiments are conducted in two indoor environments to estimate sitting posture. The results reveal the mean Euclidean distance error for all skeletal point locations is 6.65 cm. This demonstrates that our method is able to estimate various sitting changes in volunteers.

Motion artifacts (MA) significantly compromise the quality of photoplethysmographic (PPG) signals in wearable devices, hindering the accurate extraction of vital sign parameters. To address the limitations of existing methods in cross-user MA detection and the low accuracy of signal reconstruction, this paper proposes FlexiMA, a two-stage co-optimization framework that operates without reference signals. This framework is designed to tackle two key tasks: MA detection and MA removal. In the detection phase, a task-adaptive diffusion model, IMD-XResNet1D, is developed by integrating meta-learning and diffusion mechanisms, enabling efficient modeling of artifact-related features in new users. In the removal phase, an adversarial variational autoencoder (AVAE) is employed to achieve high-fidelity reconstruction of PPG signals. Experiments conducted on multi-user, multi-scenario datasets demonstrate that FlexiMA achieves 99.68% accuracy in MA detection and maintains a cross-user generalization performance of 99.32%. In the MA removal task, it attains 87.85% waveform structure similarity with an interbeat interval (IBI) error of 4.60 ms, indicating reliable signal reconstruction. These results verify the robustness and adaptability of FlexiMA in dynamic and complex environments, highlighting its strong potential for deployment in wearable applications.

Proper sitting posture is essential for health, as maintaining appropriate torso inclination improves comfort and reduces the risk of cervical and spinal disorders. Despite extensive research on posture detection, fine-grained variations in torso inclination have received limited attention. We propose TorsoTrack, a nonintrusive, device-free system for monitoring torso inclination. TorsoTrack leverages wireless respiratory signals to capture posture changes, applies signal restoration to correct abnormal segments, and extracts key features for precise angle estimation. A multilayer feature extraction network models the relationship between wireless signals and torso inclination, emphasizing critical posture features. To enhance adaptability to new users, TorsoTrack integrates a Reptile-PG meta-learning strategy, improving cross-individual prediction accuracy. Evaluations on 25 participants show that TorsoTrack reliably identifies significant features corresponding to different torso angles, achieving an average $R^{2}$ of 0.9822, RMSE of 1.6733, and MAE of 0.9977. For previously unseen individuals, the system maintains an average $R^{2}$ of 0.9033, demonstrating its effectiveness in precise torso inclination assessment.

In recent years, more and more people choose to work out at home or in the office to improve their physique and build muscle. However, the lack of professional guidance makes it difficult for many fitness practitioners to achieve optimal results. Consequently, research on noncontact fitness monitoring using wireless signals has gained attention. Existing studies primarily focus on isolated exercises, while compound exercises, which involve multiple isolated exercises, remain underexplored. This combination introduces new challenges for fitness recognition and monitoring. To this end, we propose M-Fitness, a millimeter-wave (mmWave) radar-based fitness assistant system capable of recognizing and monitoring both isolated and compound exercises. First, we capture fine-grained motion features and design image enhancement algorithms to generate intuitive motion images. Next, we design a novel motion segmentation method for fitness actions. We further formulate compound exercise recognition as a sequential task and develop customized deep learning models that allow users to incorporate new compound exercises. Finally, we perform a comprehensive fitness assessment based on the frequency, intensity, time, and type (FITT) principle. Experiments on a dataset of over 5000 movement samples from 18 volunteers demonstrate that M-Fitness achieves 96.5% accuracy for isolated exercise recognition and 92.7% accuracy for compound exercise recognition, exhibiting strong adaptability to diverse environments.