Continuous and fine-grained breathing volume monitoring from afar using wireless signals

Continuous and fine-grained breathing volume monitoring from afar using wireless signals
复制标题

DOI:
10.1109/infocom.2016.7524402
复制
发表时间:
2016-04
期刊:
IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications
影响因子:
--
通讯作者:
Phuc Nguyen;Xinyu Zhang;A. Halbower;Tam N. Vu
Phuc Nguyen;Xinyu Zhang;A. Halbower;Tam N. Vu
中科院分区:
其他
文献类型:
--
作者:
Phuc Nguyen;Xinyu Zhang;A. Halbower;Tam N. Vu

文献摘要

被引文献

相似文献

在这项工作中,我们首次提出了一种名为WiSpiro的自主系统,该系统可以在睡眠期间以高分辨率从远处连续监测人的呼吸量。WiSpiro依靠相位运动解调算法,通过分析运动对2.4 GHz定向无线电发送的连续波信号造成的细微相位变化,重建微小的胸部和腹部运动。这些运动被映射到呼吸量,其中映射关系经由短训练过程获得。为了科普身体运动,该系统跟踪人的大规模运动和姿势变化,并相应地将其发射天线移动到适当的位置,以便将其波束保持在人身体前部的特定区域。它还结合了插值机制,以解决我们的姿势检测技术可能存在的不准确性和人体的微小运动。我们已经建立了WiSpiro原型,并通过用户研究证明,它可以准确和连续地监测用户的呼吸量,准确度中位数为90%至95.4%(或0.0581至0.111的误差),甚至在身体运动的情况下。监测的粒度和准确性足够高,可用于临床医生的诊断。
In this work, we propose for the first time an autonomous system, called WiSpiro, that continuously monitors a person's breathing volume with high resolution during sleep from afar. WiSpiro relies on a phase-motion demodulation algorithm that reconstructs minute chest and abdominal movements by analyzing the subtle phase changes that the movements cause to the continuous wave signal sent by a 2.4 GHz directional radio. These movements are mapped to breathing volume, where the mapping relationship is obtained via a short training process. To cope with body movement, the system tracks the large-scale movements and posture changes of the person, and moves its transmitting antenna accordingly to a proper location in order to maintain its beam to specific areas on the frontal part of the person's body. It also incorporates interpolation mechanisms to account for possible inaccuracy of our posture detection technique and the minor movement of the person's body. We have built WiSpiro prototype, and demonstrated through a user study that it can accurately and continuously monitor user's breathing volume with a median accuracy from 90% to 95.4% (or 0.0581 to 0.111 of error) to even in the presence of body movement. The monitoring granularity and accuracy are sufficiently high to be useful for diagnosis by clinical doctor.