This article covers radar signal processing for sensing in the context of assisted living (AL). This is presented through three example applications: human activity recognition (HAR) for activities of daily living (ADL), respiratory disorders, and sleep stages (SSs) classification. The common challenge of classification is discussed within a framework of measurements/preprocessing, feature extraction, and classification algorithms for supervised learning. Then, the specific challenges of the three applications from a signal processing standpoint are detailed in their specific data processing and ad hoc classification strategies. Here, the focus is on recent trends in the field of activity recognition (multidomain, multimodal, and fusion), health-care applications based on vital signs (superresolution techniques), and comments related to outstanding challenges. Finally, this article explores challenges associated with the real-time implementation of signal processing/classification algorithms.

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.

Utilizing a radar sensor to monitor the horizontal axis wind turbine (HAWT) has been reported in the literature. However, the specific methods for monitoring its structural health have not been well studied. In this article, an overall structural health monitoring solution of HAWT using the Doppler radar sensor has been proposed, which includes parameter extraction and fault detection. Based on the time-Doppler features of the HAWT, the operational parameters, including rotational speed, downtime, and yaw time, can be accurately extracted from the spectrogram. Three kinds of faults, including blade rupture, blade surface damage, and angle mismatch, can be detected. The simulated results demonstrate that the proposed solution can effectively extract the parameters and detect the specific faults of the HAWT. Moreover, the proposed solution is also validated with real onshore wind turbines. Both results reveal the prospect of using the radar sensor for noncontact structural health monitoring of HAWT.

Time-varying vocal folds vibration information is of crucial importance in speech processing, and the traditional devices to acquire speech signals are easily smeared by the high background noise and voice interference. In this paper, we present a non-acoustic way to capture the human vocal folds vibration using a 24-GHz portable auditory radar. Since the vocal folds vibration only reaches several millimeters, the high operating frequency and the 4 × 4 array antennas are applied to achieve the high sensitivity. The Variational Mode Decomposition (VMD) based algorithm is proposed to decompose the radar-detected auditory signal into a sequence of intrinsic modes firstly, and then, extract the time-varying vocal folds vibration frequency from the corresponding mode. Feasibility demonstration, evaluation, and comparison are conducted with tonal and non-tonal languages, and the low relative errors show a high consistency between the radar-detected auditory time-varying vocal folds vibration and acoustic fundamental frequency, except that the auditory radar significantly improves the frequency-resolving power.

The vibration of the vocal folds, which directly decides the properties of voice during phonations, is an important issue for speech processing. Radar sensors with good acoustic noise rejection and directional discrimination have been widely used in time-varying vocal folds’ vibration detection. However, the specific methods for extracting multitarget vocal folds’ vibration have not been studied. In this article, we present a noncontact method based on multiple-input multiple-output (MIMO) frequency modulated continuous-wave (FMCW) radar to capture and analyze the vocal folds’ vibrations of multiple targets. The multiple signal classification (MUSIC)-based direction-of-arrival (DOA) estimation and linear constraint minimal variance (LCMV) adaptive digital beamforming (ADBF) are applied to obtain separated signals of multiple subjects. The empirical wavelet transform (EWT)-based algorithm is proposed to decompose the preprocessed signal to achieve the fundamental frequency component and extract the time-varying frequency of vocal folds’ vibration of each subject. Extensive experiments are carried out to confirm the capability of the proposed method. The results compared with the reference sensors show that the proposed method can effectively obtain vocal folds’ vibration frequency when multiple subjects speak simultaneously.