Integrated sensing and communication technologies provide essential sensing capabilities that address pressing challenges in remote health monitoring systems. However, most of today’s systems remain obtrusive, requiring users to wear devices, interfering with people’s daily activities, and often raising privacy concerns. Herein, we present HealthDAR, a low-cost, contactless, and easy-to-deploy health monitoring system. Specifically, HealthDAR encompasses three interventions: 1) symptom early detection (monitoring of vital signs and cough detection); 2) tracking and social distancing; and 3) preventive measures (monitoring of daily activities, such as face-touching and hand-washing). HealthDAR has three key components: 1) a low-cost, low-energy, and compact integrated radar system; 2) a simultaneous signal processing combined deep learning (SSPDL) network for cough detection; and 3) a deep learning method for the classification of daily activities. Through performance tests involving multiple subjects across uncontrolled environments, we demonstrate HealthDAR’s practical utility for health monitoring.

Reconstruction-based and prediction-based approaches are widely used for video anomaly detection (VAD) in smart city surveillance applications. However, neither of these approaches can effectively utilize the rich contextual information that exists in videos, which makes it difficult to accurately perceive anomalous activities. In this paper, we exploit the idea of a training model based on the “Cloze Test” strategy in natural language processing (NLP) and introduce a novel unsupervised learning framework to encode both motion and appearance information at an object level. Specifically, to store the normal modes of video activity reconstructions, we first design an optical stream memory network with skip connections. Secondly, we build a space–time cube (STC) for use as the basic processing unit of the model and erase a patch in the STC to form the frame to be reconstructed. This enables a so-called ”incomplete event (IE)” to be completed. On this basis, a conditional autoencoder is utilized to capture the high correspondence between optical flow and STC. The model predicts erased patches in IEs based on the context of the front and back frames. Finally, we employ a generating adversarial network (GAN)-based training method to improve the performance of VAD. By distinguishing the predicted erased optical flow and erased video frame, the anomaly detection results are shown to be more reliable with our proposed method which can help reconstruct the original video in IE. Comparative experiments conducted on the benchmark UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets demonstrate AUROC scores reaching 97.7%, 89.7%, and 75.8%, respectively.

Nowadays, it is still a great challenge to detect and locate indoor humans using a frequency-modulated continuous-wave radar accurately. Due to the interference of the indoor environment and complex objects such as green plants, the radar signal may penetrate, reflect, refract, and scatter, and the echo signals will contain noise, clutter, and multipath of different characteristics. Therefore, a method combined with comprehensive non-target signal removal and human localization is proposed to achieve position estimation of a human target. Time-variant clutter is innovatively mitigated through time accumulation using point clustering. Ghost targets are reduced according to propagation path matching. The experimental results show that the method can locate the real target human within an average error of 0.195 m in multiple complex environments with green plants, curtains, or furniture using a 77 GHz millimeter-wave radar. Meanwhile, the proposed method performs better than conventional methods. The detection probability is 81.250% when the human is behind a potted plant and is 90.286% when beside it.

In this work, a combined system for vehicle occupant detection and non-contact vital sign monitoring is proposed which can be used in the automotive industry. First, an occupant detection and radial range-azimuth positioning method based on frequency modulated continuous wave (FMCW) radar is applied. By separating the radar echoes of multiple life targets, the intermediate frequency (IF) signals containing vital sign micro-movement information of each passenger’s chest are extracted. And then the successive variational mode decomposition (SVMD) algorithm is used to decompose and reconstruct the breathing and heartbeat signals of each passenger. Furthermore, we propose an IF signal speed compensation method to eliminate the impact of random body movement (RBM) on vital signal extraction. Our system can successfully extract the breathing and heartbeat signals of multiple passengers in the cabin. The average estimation accuracy of the breathing rate (BR) and heart rate (HR) of a single target in different physical states at a distance of 1.5m can reach 91.6% and 91.9% respectively. And the proposed RBM correction algorithm can significantly improve the distortion of vital signals caused by radial RBM.

Gesture plays an important role in human–machine interaction. However, the insufficient accuracy and high complexity of gesture recognition have blocked its widespread application. A gesture recognition method that combines state machine and bidirectional long short-term memory (Bi-LSTM) fusion neural network is proposed to improve the accuracy and efficiency. Firstly, gestures with large movements are categorized into simple trajectory gestures and complex trajectory gestures in advance. Afterwards, different recognition methods are applied for the two categories of gestures, and the final result of gesture recognition is obtained by combining the outputs of the two methods. The specific method used is a state machine that recognizes six simple trajectory gestures and a bidirectional LSTM fusion neural network that recognizes four complex trajectory gestures. Finally, the experimental results show that the proposed simple trajectory gesture recognition method has an average accuracy of 99.58%, and the bidirectional LSTM fusion neural network has an average accuracy of 99.47%, which can efficiently and accurately recognize 10 gestures with large movements. In addition, by collecting more gesture data from untrained participants, it was verified that the proposed neural network has good generalization performance and can adapt to the various operating habits of different users.