DeepVS: a deep learning approach for RF-based vital signs sensing
DeepVS: a deep learning approach for RF-based vital signs sensing
复制标题
DOI：
10.1145/3535508.3545554
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Zongxing Xie;Hanrui Wang;Song Han;E. Schoenfeld;Fan Ye
中科院分区：
文献类型：
--
作者：
Zongxing Xie;Hanrui Wang;Song Han;E. Schoenfeld;Fan Ye
生命体征(例如，心率和呼吸率)是健康状况评估的指标。已经努力使用射频(RF)技术(例如，Wi-Fi、FMCW、UWB)来提取生命体征，这些技术为无需用户合作的连续和无处不在的监测提供了非接触式解决方案。虽然基于射频的生命体征监测是用户友好的，但其健壮性面临两个挑战。一方面，射频信号是由心跳和呼吸引起的周期性胸壁位移以非线性方式调制的。在心率和呼吸频率(HR和RR)存在高次谐波以及HR和RR之间互调的情况下，特别是当它们具有重叠的频段时，很难识别它们。另一方面，不经意的身体运动可能会干扰和失真射频信号，压倒生命信号，从而抑制对生理运动(即心跳和呼吸)的参数估计。在本文中，我们提出了深度学习方法DeepVS，它以统一的方式解决了上述非线性和无意运动对基于射频的健壮生命体征传感的挑战。DeepVS结合了一维CNN和注意力模型来利用局部特征和时间相关性。此外，它利用双流方案来集成来自时间域和频率域的特征。此外，DeepVS使用多头结构统一了HR和RR的估计，这只会给现有模型增加有限的额外开销(<；1%)，而不是分别使用HR和RR的两个独立模型将开销增加一倍。我们的实验表明，DeepVS在具有挑战性的数据集上实现了7.4/4.9次/分钟(Bpm)的80%HR/RR误差，而非学习型解决方案的误差为11.8/7.3次/分。此外，还进行了消融研究，以量化DeepVS的效果。
Vital signs (e.g., heart and respiratory rate) are indicative for health status assessment. Efforts have been made to extract vital signs using radio frequency (RF) techniques (e.g., Wi-Fi, FMCW, UWB), which offer a non-touch solution for continuous and ubiquitous monitoring without users' cooperative efforts. While RF-based vital signs monitoring is user-friendly, its robustness faces two challenges. On the one hand, the RF signal is modulated by the periodic chest wall displacement due to heartbeat and breathing in a nonlinear manner. It is inherently hard to identify the fundamental heart and respiratory rates (HR and RR) in the presence of higher order harmonics of them and intermodulation between HR and RR, especially when they have overlapping frequency bands. On the other hand, the inadvertent body movements may disturb and distort the RF signal, overwhelming the vital signals, thus inhibiting the parameter estimation of the physiological movement (i.e., heartbeat and breathing). In this paper, we propose DeepVS, a deep learning approach that addresses the aforementioned challenges from the non-linearity and inadvertent movements for robust RF-based vital signs sensing in a unified manner. DeepVS combines 1D CNN and attention models to exploit local features and temporal correlations. Moreover, it leverages a two-stream scheme to integrate features from both time and frequency domains. Additionally, DeepVS unifies the estimation of HR and RR with a multi-head structure, which only adds limited extra overhead (<1%) to the existing model, compared to doubling the overhead using two separate models for HR and RR respectively. Our experiments demonstrate that DeepVS achieves 80-percentile HR/RR errors of 7.4/4.9 beat/breaths per minute (bpm) on a challenging dataset, as compared to 11.8/7.3 bpm of a non-learning solution. Besides, an ablation study has been conducted to quantify the effectiveness of DeepVS.