SpiroMilli: Bringing Ad-hoc Spirometry to 5G Devices

Figure 1: (a) Exhalation on a mmWave device; (b) Phase of the reflected signal shows tiny vibrations during airflow; (c) Timesynchronized vibration signals from multiple phased-array antennas; (d) Signal processing to improve fidelity, track moving reflectors, and estimate distance-invariant vibration; (e) CNN-LSTMarchitecture tomap physical vibration to 7 key spirometry indicators; and (f) Predicted flow rate in comparison to ground-truth for two subjects.

[1]  Kristie B. Hadden,et al.  2020 , 2020, Journal of Surgical Orthopaedic Advances.

[2]  Mario Konijnenburg,et al.  CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment , 2019, IEEE Transactions on Biomedical Circuits and Systems.