TY - GEN
T1 - Data fusion of single-Tag RFID measurements for respiratory rate monitoring
AU - Mongan, W.
AU - Ross, R.
AU - Rasheed, I.
AU - Liu, Y.
AU - Ved, K.
AU - Anday, E.
AU - Dandekar, K.
AU - Dion, G.
AU - Kurzweg, T.
AU - Fontecchio, A.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85050655915&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050655915&partnerID=8YFLogxK
U2 - 10.1109/SPMB.2017.8257028
DO - 10.1109/SPMB.2017.8257028
M3 - Conference contribution
T3 - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings
SP - 1
EP - 6
BT - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017
Y2 - 2 December 2017
ER -