RF Vital Sign Sensing under Free Body Movement

Abstract

Radio frequency (RF) sensors such as radar are instrumental for continuous, contactless sensing of vital signs, especially heart rate (HR) and respiration rate (RR). However, decades of related research mainly focused on static subjects, because the motion artifacts from other body parts may easily overwhelm the weak reflections from vital signs. This paper marks a first step in enabling RF vital sign sensing under ambulant daily living conditions. Our solution is inspired by existing physiological research that revealed the correlation between vital signs and body movement. Specifically, we propose to combine direct RF sensing for static instances and indirect vital sign prediction based on movement power estimation. We design customized machine learning models to capture the sophisticated correlation between RF signal pattern, movement power, and vital signs. We further design an instant calibration and adaptive training scheme to enable cross-subjects generalization, without any explicit data labeling from unknown subjects. We prototype and evaluate the framework using a commodity radar sensor. Under a variety of moving conditions, our solution demonstrates an average estimation error of 5.57 bpm for HR and 3.32 bpm for RR across multiple subjects, which largely outperforms state-of-the-art systems.

Extending Reliability of mmWave Radar Tracking and Detection via Fusion With Camera

“…Specifically, the work [25] applies SVD subspace decomposition to improve the localization and ICA to obtain vital signs. And the work [42] utilizes LSTMbased deep neural network to estimate heart and breath rates in dynamic scenarios.…”

“…Baselines. We compare our scheme with two state-ofthe-art works based on SVD+ICA [25] and long-short-termmemory (LSTM) [42]. Specifically, the work [25] applies SVD subspace decomposition to improve the localization and ICA to obtain vital signs.…”

Few-Shot User-Adaptable Radar-Based Breath Signal Sensing

“…As also mentioned by the authors, the classical FFT approach does not guarantee the correct prediction of vital parameters in motion-corrupted scenarios. Gong et al [ 35 ] illustrate an FMCW-based solution for vital sign estimation that also seeks to address the problem of sensing even in the presence of motion. The approach combines direct FMCW sensing for static instances with an indirect vital sign prediction based on motion power estimation.…”

“…The belt is used as a reference to measure displacement in N (Newtons). We chose to use this belt as a reference since it is employed in other state-of-the-art work for benchmarking with radar solutions such as [ 35 , 36 ]. As reported in these works, the belt has a force resolution of 0.1 Newton.…”

Stepping Into the Next Decade of Ubiquitous and Pervasive Computing: UbiComp and ISWC 2021

“…48 In addition to exploiting hardware capabilities, session presenters showcased their effort to enable novel applications, such as approximating the traditionally bulky Synthetic Aperture Rader imaging with mmWave, 49 recognizing the shape and material of an object simultaneously and noninvasively through RFID tag, and sensing liquid level in a container utilizing existing home WiFi network. 50 Presenters were specifically keen on clinical and health applications, such as vital sensing, 51 infusion drip rate monitoring, 52 and long-range multitarget respiration sensing. 53…”