Data fusion of single-tag rfid measurements for respiratory rate monitoring
Data fusion of single-tag rfid measurements for respiratory rate monitoring
复制标题
DOI：
10.1109/spmb.2017.8257028
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
W. Mongan;R. Ross;I. Rasheed;Y. Liu;K. Ved;E. Anday;K. Dandekar;G. Dion;T. Kurzweg;A. Fontecchio
中科院分区：
文献类型：
--
作者：
W. Mongan;R. Ross;I. Rasheed;Y. Liu;K. Ved;E. Anday;K. Dandekar;G. Dion;T. Kurzweg;A. Fontecchio
使用无线、被动、可穿戴、针织、智能服装设备，我们监控可以通过应变计传感器观察到的生物反馈。这种生物反馈包括呼吸活动、分娩期间的子宫监测以及预防深静脉血栓(DVT)的定期运动。由于无线应变仪中存在的噪声伪影和信号本身可能的非平稳性质，需要超越傅里叶变换的信号分析来提取观察到的运动伪影的属性。我们通过融合单个射频识别(RFID)标签的多个特征来提高该标签的实用性，以便精确地确定运动伪影的频率和大小。在本文中，我们激发了对基于RFID的应变计分析的多特征方法的需求，将原始的RFID询问器测量结果修正为特征，使用高斯混合模型和期望最大化来融合这些特征，并将呼吸频率检测的均方误差从9提高到6。
Using wireless, passive, wearable, knitted, smart garment devices, we monitor biofeedback that can be observed via strain gauge sensors. This biofeedback includes respiratory activity, uterine monitoring during labor and delivery, and regular movements to prevent Deep Vein Thrombosis (DVT). Due to noise artifacts present in a wireless strain gauge monitor and the possibly non-stationary nature of the signal itself, signal analysis beyond the Fourier transform is needed to extract the properties of the observed motion artifacts. We improve the utility of a single Radio Frequency Identification (RFID) tag by fusing multiple features of the tag, in order to precisely determine the frequency and magnitude of motion artifacts. In this paper, we motivate the need for a multi-feature approach to RFID-based strain gauge analysis, correct raw RFID interrogator measurements into features, fuse those features using a Gaussian Mixture Model and expectation maximization, and improve respiratory rate detection from 9 to 6 mean squared error over prior work.