Sleep staging is to score the sleep state of a subject into different sleep stages such as Wake and Rapid Eye Movement (REM). It plays an indispensable role in the diagnosis and treatment of sleep diseases. As manual sleep staging through well-trained sleep experts is time consuming, tedious, and subjective, many automatic methods have been developed for accurate, efficient, and objective sleep staging. Recently, deep learning based methods have been successfully proposed for EEG based sleep staging with promising results. However, most of these methods directly take EEG raw signals as input of convolutional neural networks (CNNs) without considering the domain knowledge of EEG staging. Apart from that, to capture temporal information, most of the existing methods utilize recurrent neural networks such as LSTM (Long Short Term Memory) which are not effective for modelling global temporal context and difficult to train. Therefore, inspired by the clinical guidelines of sleep staging such as AASM (American Academy of Sleep Medicine) rules where different stages are generally characterized by EEG waveforms of various frequencies, we propose a multi-scale deep architecture by decomposing an EEG signal into different frequency bands as input to CNNs. To model global temporal context, we utilize the multi-head self-attention module of the transformer model to not only improve performance, but also shorten the training time. In addition, we choose residual based architecture which makes training end-to-end. Experimental results on two widely used sleep staging datasets, Montreal Archive of Sleep Studies (MASS) and sleep-EDF datasets, demonstrate the effectiveness and significant efficiency (up to 12 times less training time) of our proposed method over the state-of-the-art.

In this paper, a noncontact breathing disorder recognition system has been proposed for identifying irregular breathing patterns. The proposed system consists of a Doppler radar-based sensor module and a machine-learning-based breathing disorder recognition module. A custom-designed 2.4-GHz continuous wave (CW) digital-IF Doppler radar is utilized as the radar sensor module to accurately capture the time-domain breathing waveform. Then a recognition module is designed with selected features and optimized classifiers. Four sets of experiments have been carried out to evaluate the proposed system comprehensively. In which, for the laboratorial experiments, the proposed system achieves 94.7 % classification accuracy using the linear SVM classifier with seven selected features. Results of clinical experiments demonstrate the feasibility of long-term breathing disorder recognition with good accuracy and robustness, and illustrate the potential of the proposed solution for the auxiliary diagnosis of diseases.

Targets located at the same distance are easily neglected in most through-wall multiple targets detecting applications which use the single-input single-output (SISO) ultra-wideband (UWB) radar system. In this paper, a novel multiple targets vital signs tracking algorithm for through-wall detection using SISO UWB radar has been proposed. Taking advantage of the high-resolution decomposition of the Variational Mode Decomposition (VMD) based algorithm, the respiration signals of different targets can be decomposed into different sub-signals, and then, we can track the time-varying respiration signals accurately when human targets located in the same distance. Intensive evaluation has been conducted to show the effectiveness of our scheme with a 0.15 m thick concrete brick wall. Constant, piecewise-constant and time-varying vital signs could be separated and tracked successfully with the proposed VMD based algorithm for two targets, even up to three targets. For the multiple targets’ vital signs tracking issues like urban search and rescue missions, our algorithm has superior capability in most detection applications.

Sleep stage estimation is crucial to the evaluation of sleep quality and is a proven biometric in diagnosing cardiovascular diseases. In this paper, we design a CW Doppler radar to accurately measure sleep-related signals, including respiration, heartbeat and body movement. Body movement index (BMI), respiration per minute (RPM), variance of RPM, amplitude difference accumulation (ADA) of respiration, rapid eye movement (REM) parameter, sample entropy, heartbeat per minute (HPM), variance of HPM, ADA of heartbeat, deep parameter, and time feature have been extracted and fed into different machine learning classifiers. A total of 11 all night polysomnography (PSG) recordings from 13 healthy examinees were used to validate the proposed CW Doppler radar system and the ability to detect sleep stage information from it. Comparative studies and statistical results have shown that the Subspace K-Nearest Neighbor (KNN) algorithm outperforms the other classifiers with the highest accuracy of up to 86.6%. With the ReliefF algorithm, features have been ranked and the selected feature subsets have been preliminary tested to identify the optimal feature subset. Meanwhile, comparative analysis of our classification performance under different sleep stage patterns with prior works has been carried out to show the significant improvements over state-of-the-art solutions. These results suggest that the proposed scheme is suitable for long-term sleep monitoring.

The Doppler radar has been widely used in respiration detection. However, most of the existing microwave respiration detection works are intended for either a single human subject in front of the radar or multiple subjects with known positions. In this article, a system based on single-input-multiple-output (SIMO) continuous-wave (CW) radar equipped with adaptive digital beamforming (ADBF) technique is presented to detect the respiration of multiple human subjects at unknown positions simultaneously. A solution based on the modified Capon (m-Capon) direction-of-arrival (DOA) estimation and linear constraint minimal variance (LCMV) ADBF is proposed to automatically find the angles of human subjects. By forming spatially distributed beams toward the subjects of interest, human respiration can be remotely obtained. Furthermore, for the detection of each person's respiration, nulls are also generated at the angles of nearby interfering subjects, which results in high target discrimination capability when multiple human subjects are close to each other. The experimental results show good detection accuracy compared with the reference sensor, which verifies the effectiveness of the developed system for multitarget respiration detection.

Remote techniques for measuring human vital signs have attracted great interests due to the benefits shown in medical monitoring and military applications. Compared with continuous-wave Doppler radar, frequency-modulated continuous-wave (FMCW) radar which can discriminate vital signs from different distances, shows potential for reducing the interferences from other targets and the environment. However, in the state-of-the-art algorithms, only one chirp per frame is utilized for FMCW-based vital sign monitoring. Moreover, the vital signal is extracted from only one range bin of the fast Fourier transform. Which does not make full utilization of the long system idle time, and loses the power distributed on other range bins. By exploiting the relationship between respiration and heartbeat vibrations, an adaptive identification embedded ensemble empirical mode decomposition (EEMD) method for joint-range spectral estimation is proposed to measure the heart rate. First, A multi-chirp processing is presented for a 2- dimensional phase accumulation. Then the phase signals from a sequence of range bins are decomposed with a fast adaptive identification process. Finally, with the identified heartbeat components, we solve a multiple measurement vectors problem to estimate the heart rate. Experimental results showed that, at the detection range from 1 m~2.5 m, the proposed method can robustly distinguish the heartbeat from respiration and its harmonics and accurately estimate the heart rate with a root mean square error less than 6 bpm.