This paper demonstrates a new technology that can infer a person's emotions from RF signals reflected off his body. EQ-Radio transmits an RF signal and analyzes its reflections off a person's body to recognize his emotional state (happy, sad, etc.). The key enabler underlying EQ-Radio is a new algorithm for extracting the individual heartbeats from the wireless signal at an accuracy comparable to on-body ECG monitors. The resulting beats are then used to compute emotion-dependent features which feed a machine-learning emotion classifier. We describe the design and implementation of EQ-Radio, and demonstrate through a user study that its emotion recognition accuracy is on par with state-of-the-art emotion recognition systems that require a person to be hooked to an ECG monitor.

/pdf/emotion-recognition-using-wireless-signals-d4xk1cgrib.pdf

Emotion recognition using wireless signals

Ultra-wideband (UWB) pulse Doppler radars can be used for noncontact vital signs monitoring of more than one subject. However, their detected signals typically have low signal-to-noise ratio (SNR) causing significant heart rate (HR) detection errors, as the spurious harmonics of respiration signals and mixed products of respiration and heartbeat signals (that can be relatively higher than heartbeat signals) corrupt conventional fast Fourier transform spectrograms. In this paper, we extend the complex signal demodulation (CSD) and arctangent demodulation (AD) techniques previously used for accurately detecting the phase variations of reflected signals of continuous wave radars to UWB pulse radars as well. These detection techniques reduce the impact of the interfering harmonic signals, thus improving the SNR of the detected vital sign signals. To further enhance the accuracy of the HR estimation, a recently developed state-space method has been successfully combined with CSD and AD techniques and over 10 dB improvements in SNR is demonstrated. The implementation of these various detection techniques has been experimentally investigated and full error and SNR analysis of the HR detection are presented.

Phase-Based Methods for Heart Rate Detection Using UWB Impulse Doppler Radar

Heart rate (HR) estimation and monitoring is of great importance to determine a person’s physiological and mental status. Recently, it has been demonstrated that HR can be remotely retrieved from facial video-based photoplethysmographic signals captured using professional or consumer-level cameras. Many efforts have been made to improve the detection accuracy of this noncontact technique. This paper presents a timely, systematic survey on such video-based remote HR measurement approaches, with a focus on recent advancements that overcome dominating technical challenges arising from illumination variations and motion artifacts. Representative methods up to date are comparatively summarized with respect to their principles, pros, and cons under different conditions. Future prospects of this promising technique are discussed and potential research directions are described. We believe that such a remote HR measurement technique, taking advantages of unobtrusiveness while providing comfort and convenience, will be beneficial for many healthcare applications.

Video-Based Heart Rate Measurement: Recent Advances and Future Prospects

Physiological signs can be remotely observed from the physiological and physical effects caused by a cardiorespiratory activity. A wide range of research on remote cardiorespiratory monitoring systems has been done using different methods, including methods based on Doppler effect, thermal imaging, and video camera imaging. The aim of this paper was to review and compare the newest and most promising of such remote measuring methods, introducing their merits and limitations under different circumstances. In addition, this paper summarizes the performance of these methods in a table regarding the noise artifacts, subject movement, the number of regions of interest, generalization to multiple subjects, detection range (distance), biological effects, and cost. This is a thorough general overview of the remote measurement of cardiorespiratory methods.

Monitoring of Cardiorespiratory Signal: Principles of Remote Measurements and Review of Methods

A survey of radar systems used in the medical field is presented. First, medical applications of radars are described, and some emerging research fields are highlighted. Then, medical radars are analyzed in terms of block diagrams and behavioral equations and some implementations are shown as examples. A section is dedicated to the radiating structures used in these radars. Finally, human safety and environmental impact issues are addressed. The most investigated medical applications of radars are breast tumor diagnostics and remote monitoring of cardiorespiratory activity. New fields of interest are physiological liquid detection, and the monitoring of artery walls and vocal cord movements. Among the various topologies, continuous wave (CW) radars have been proven to yield the highest range resolution that is limited only by the system noise while the resolution of ultra wideband (UWB) and frequency modulated continuous wave (FMCW) radars is also related to the used frequency bandwidth. Concerning the maximum range, UWB radars have the best performance due to their ability to operate in the presence of environmental clutter. As for the radiating structures, planar antennas are preferred for diagnostic applications, due to their small dimensions and good matching when placed in contact with the human body. Radar systems for remote monitoring, instead, are designed by using high gain antennas and taking into account the complex radar cross section (RCS) of the body.

A survey of radar systems for medical applications

The designed sensor enables accurate reconstruction of chest-wall movement caused by cardiopulmonary activities, and the algorithm enables estimation of respiration, heartbeat rate, and some indicators of heart rate variability (HRV). In particular, quadrature receiver and arctangent demodulation with calibration are introduced for high linearity representation of chest displacement; 24-bit ADCs with oversampling are adopted for radar baseband acquisition to achieve a high signal resolution; continuous-wavelet filter and ensemble empirical mode decomposition (EEMD) based algorithm are applied for cardio/pulmonary signal recovery and separation so that accurate beat-to-beat interval can be acquired in time domain for HRV analysis. In addition, the wireless sensor is realized and integrated on a printed circuit board compactly. The developed sensor system is successfully tested on both simulated target and human subjects. In simulated target experiments, the baseband signal-to-noise ratio (SNR) is 73.27 dB, high enough for heartbeat detection. The demodulated signal has 0.35% mean squared error, indicating high demodulation linearity. In human subject experiments, the relative error of extracted beat-to-beat intervals ranges from 2.53% to 4.83% compared with electrocardiography (ECG) R-R peak intervals. The sensor provides an accurate analysis for heart rate with the accuracy of 100% for p = 2% and higher than 97% for p = 1%.

Noncontact Accurate Measurement of Cardiopulmonary Activity Using a Compact Quadrature Doppler Radar Sensor

The ability to remotely detect vital signs such as heartbeat and respiration is particularly useful in situations where contact electrocardiography or other electrodes are impractical or inconvenient. Compared with traditionally way such as electrocardiogram (ECG) or photoplethysmography (PPG), noncontact detection technology is more suitable for sleep apnea monitoring, infant SIDS monitoring, fatigue monitoring, in-hospital monitoring, and home health care. Previous efforts have demonstrated that microwave Doppler radar has potential to provide a practical tool for noncontact detecting cardiopulmonary movement [1, . Recently, much interest has been paid to the topic of noncontact cardiopulmonary monitoring using a microwave Doppler radar. Doppler radar uses Doppler Effect of waves to detecting the chest displacement of a target and give out a down-conversion signal which is related to the body movement due to respiration, heartbeat and other noises. The mainly challenge for using Doppler radar for cardiopulmonary monitoring includes recovery and separation of the heartbeat and respiration signal, and removal the interference signal caused by body motion and background, in addition, the radar signal processing algorithm should be robust for the changes in the signal waveform that occur due to the measurement position. In this paper, a Noncontact Sensor of Vital Signs was realized basd on continuous wave (CW) Doppler radar, in addition, real-time signal processing was studied for single target noncontact cardiopulmonary monitoring. As Fig.1, the sensor module faced a human body seated at a distance varying from 0.2 to 1.0 meters, in which the Doppler radar worked on 10GHz, with an oscillator, a mixer and PCB antennas. The mixed intermediate frequency (IF) signal of radar was filtered and amplified by 2-order Bessel LPF and HPF to extract the interesting signal range from 0.1Hz to 100Hz (Fig. 2). After that, the conditioned signal was acquired to the computer via NIDAQ 6215 with 16 bits ADC and 2000 sample rate. A pressure pulse wave sensor was employed in the system to provide a reference signal for heartbeat signal. Digital signal processing for Doppler radar was implemented on a laptop based on Visual Basic 6.0. First, two band-pass filters were used to separate the heartbeat and respiration signal, for each of them short-time Fourier transform was employed to acquire real-time spectral information. After that, we used Sinc function as interpolation method to improve the accuracy of the spectrum, and then we searched the peak of the interpolated spectrum for each time point and converted it to real-time heart and respiration rate (Fig. 3). Algorithms used in this paper were studied and the performances were evaluated by comparing them with reference. In conclusion, the Doppler radar based sensor in this paper can acquire signal about vital signs meeting the need of noncontact single target cardiopulmonary monitoring up to 1m, and the sensor is portable and convenient to use in health care application. The shorttime Fourier transform and Sinc interpolation method for Doppler radar signal processing can improve the accuracy and response speed considerably, compared with traditional FFT. It has raletively small amount of calculation, which is more conductive in real-time processing situation than using complicated algorithm such as CWT .

Fujiang Lin

Papers

Noncontact Accurate Measurement of Cardiopulmonary Activity Using a Compact Quadrature Doppler Radar Sensor

Cardiopulmonary Monitoring Research Based on Noncontact Sensor of Vital Signs