CardiacWave

Abstract

Using wireless signals to monitor human vital signs, especially heartbeat information, has been intensively studied in the past decade. This non-contact sensing modality can drive various applications from cardiac health, sleep, and emotion management. Under the circumstance of the COVID-19 pandemic, non-contact heart monitoring receives increasingly market demands. However, existing wireless heart monitoring schemes can only detect limited heart activities, such as heart rate, fiducial points, and Seismocardiography (SCG)-like information. In this paper, we present CardiacWave to enable a non-contact high-definition heart monitoring. CardiacWave can provide a full spectrum of Electrocardiogram (ECG)-like heart activities, including the details of P-wave, T-wave, and QRS complex. Specifically, CardiacWave is built upon the Cardiac-mmWave scattering effect (CaSE), which is a variable frequency response of the cardiac electromagnetic field under the mmWave interrogation. The CardiacWave design consists of a noise-resistant sensing scheme to interrogate CaSE and a cardiac activity profiling module for extracting cardiac electrical activities from the interrogation response. Our experiments show that the CardiacWave-induced ECG measures have a high positive correlation with the heart activity ground truth (i.e., measurements from a medical-grade instrument). The timing difference of P-waves, T-waves, and QRS complex is 0.67%, 0.71%, and 0.49%, respectively, and a mean cardiac event difference is within a delay of 5.3 milliseconds. These results indicate that CaridacWave offers high-fidelity and integral heart clinical characteristics. Furthermore, we evaluate the CardiacWave system with participants under various conditions, including heart and breath rates, ages, and heart habits (e.g., tobacco use).

Machine Learning in RADAR-based Physiological Signals Sensing: A Scoping Review of the Models, Datasets and Metrics

“…We include papers regarding a fine-grained reconstruction of both a physiological signal or simplified waveform derived from a physiological signal. We find papers about the reconstruction of the electrocardiogram (ECG) (n = 3) [32], [36], [63], the seismocardiogram (SCG) [44] (n = 1) and the photoplethismogram (PPG) (n = 2) [69], [72]; then we find papers dealing with respiratory waveform (n = 4) [68], [71], [90], [94] or simplified version of the cardiac waveform (n = 4) [35], [41], [60], [73] or both (n = 2) [30], [77].…”

“…[23], [30], [32], [35], [36], [41], [44], [60], [63], [68]- [73], [77], [90], [94] Physiological event detection (n = 7)…”

“…Among these 9, 6 consider simple movements patterns, with the subject moving mainly their limbs (e.g. performing home gym exercise, cycling, treadmill, random body movements in stationary position, sit to stand) [17], [29], [30], [63], [68], whereas the remaining 3 test their proposed approach in complex moving scenarios [40], [72], [94] (e.g. walking, activity of daily living).…”

A Survey of mmWave-Based Human Sensing: Technology, Platforms and Applications

“…Different from these works, CardiacWave [101] recovers vital signs by analyzing the electromagnetic (EM) field changes rather than the chest movements brought by the heart. CardiacWave presents a novel and interesting observation: the electromagnetic field induced by cardiac electrical activity will modulate the chest-scattered mmWave signals, called Cardiac-mmWave scattering effect (CaSE).…”

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

“…In the included papers, ablation studies take the form of performance evaluation comparisons based on: user-related components, device-related components, environmental components, experimental components, and domain-specific components. In particular user-related components include user motion and orientation during data collection in sleep posture monitoring [148], breathing monitoring [43], gesture recognition [76], user identification [117], and heart activity monitoring [142], as well as aesthetics, such as hair or clothing in fine-grained activity sensing [71], breathing and vital sign monitoring [43,136], and user identification [44,145]. Device-related components include device type, sampling rate, and operating system, as well as device placement and orientation in activity and gaze tracking [53,71], vital sign monitoring and physiological sensing [78,136], speech recognition via built-in sensors and speech synthesis [73,125], and user behavior sensing [60].…”