Healthcare automation technologies have led to develop “smart” home with intelligent sensing systems to fully monitor vital signs. One important healthcare application of the millimeter-wave radar sensor is the respiratory rate (RR) estimation. Accurate and robust measurements of respiration motion and RR estimation in nonhospital facilities is a challenging task. We present a novel contactless on-bed radar system for respiration monitoring for “smart” home. A simplified trunk model and a mode-decomposition-based respiration reconstruction are designed for analysis of 2-D radar profile to extract nonstationary breathing motion information. Resting breathing experiments with different respiratory patterns and human poses are performed to evaluate the performance of the proposed system. The results show that the system measures respiration-induced body movement with a root-mean-squared error of 0.31 mm and a mean accuracy of 89.6%. For RR estimation, the overall accuracy is 97.1% under normal respiratory patterns and 93.4% under abnormal respiratory patterns.

Growing aging population highlights the importance of managing chronic diseases. The rapid development of Internet of Things (IoT) and big data analysis makes it feasible and affordable to monitor and manage chronic diseases for caring at home. The process of chronic diseases management involves monitoring rehabilitation and recovery, tracking physiological and behavioral status, and health condition classification and diagnosis. In this paper, we proposed a framework for monitoring and management of home care elderly adults. A three-level architecture, which is IoT-Intelligent Terminal(IT)-Cloud, is established to achieve data acquisition, signal transmission, remote interaction and diagnosis. Five diagnosis methods including Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K Near Neighbor (KNN), and Back Process Neural Network (BPNN) are implemented to evaluate the risk of suffering from heart disease and experiments showed the accuracy is over 95%. Experimental result reveals that the data flow and remote interaction in this system are effective and primary diagnosis is validated.

Noncontact vital sign monitoring based on radar has attracted great interest in many fields. Heart Rate Variability (HRV), which measures the fluctuation of heartbeat intervals, has been considered as an important indicator for general health evaluation. This paper proposes a new algorithm for HRV monitoring in which frequency-modulated continuous-wave (FMCW) radar is used to separate echo signals from different distances, and the beamforming technique is adopted to improve signal quality. After the phase reflecting the chest wall motion is demodulated, the acceleration is calculated to enhance the heartbeat and suppress the impact of respiration. The time interval of each heartbeat is estimated based on the smoothed acceleration waveform. Finally, a joint optimization algorithm was developed and is used to precisely segment the acceleration signal for analyzing HRV. Experimental results from 10 participants show the potential of the proposed algorithm for obtaining a noncontact HRV estimation with high accuracy. The proposed algorithm can measure the interbeat interval (IBI) with a root mean square error (RMSE) of 14.9 ms and accurately estimate HRV parameters with an RMSE of 3.24 ms for MEAN (the average value of the IBI), 4.91 ms for the standard deviation of normal to normal (SDNN), and 9.10 ms for the root mean square of successive differences (RMSSD). These results demonstrate the effectiveness and feasibility of the proposed method in emotion recognition, sleep monitoring, and heart disease diagnosis.

The measurement of blood oxygen saturation in the prefrontal cortex (PFC), especially during sleep, is of great significance for clinical research. Herein, we present a wearable PFC oxygen saturation measurement system using dual-wavelength functional near-infrared spectroscopy. The system is well designed for user-friendly donning and has the advantages of comfort, convenience, portability, and affordability. The performance of the proposed system is investigated by the calibration and experimental results. The wearable system has demonstrated great potential to conduct the physiological monitoring of PFC, and it can be widely deployed in daily life.

Correct and continuous weight measurement of a burn patient is important for fluid resuscitation. Generally, a body weight bed uses four sensors to obtain signals. However, owing to signals dynamic characteristics, the air fluidized therapy bed has a large error in this mode, which is difficult to reduce. In this study, we optimized the sensor configuration scheme and developed a set of signal processing and methods to evaluate noise reduction. Additionally, the wavelet neural network was used to improve the weighing accuracy. Furthermore, medical tools are located on different body parts of a patient to acquire weight characteristics to assist with the rehydration of patient. The average error of 183.33g is acceptable from a medical perspective. An average error of 250.21g in dynamic weight after using wavelet de-noising and wavelet neural network methods was obtained.