US 12,127,825 B2
Sleep tracking and vital sign monitoring using low power radio waves
Dongeek Shin, Santa Clara, CA (US); Brandon Barbello, Mountain View, CA (US); Shwetak Patel, Seattle, WA (US); Anupam Pathak, San Carlos, CA (US); and Michael Dixon, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 17/608,319
Filed by Google LLC, Mountain View, CA (US)
PCT Filed May 8, 2019, PCT No. PCT/US2019/031290
§ 371(c)(1), (2) Date Nov. 2, 2021,
PCT Pub. No. WO2020/226638, PCT Pub. Date Nov. 12, 2020.
Prior Publication US 2022/0218224 A1, Jul. 14, 2022
Int. Cl. A61B 5/0507 (2021.01); A61B 5/00 (2006.01); A61B 5/024 (2006.01); A61B 5/08 (2006.01); A61B 5/11 (2006.01); G01S 13/28 (2006.01)
CPC A61B 5/0507 (2013.01) [A61B 5/024 (2013.01); A61B 5/0816 (2013.01); A61B 5/1116 (2013.01); A61B 5/4815 (2013.01); A61B 5/6898 (2013.01); A61B 5/725 (2013.01); A61B 5/7267 (2013.01); G01S 13/282 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A smart-home device that performs radar-based measurement of vital signs, the smart-home device comprising:
a housing;
an RF emitter located within the housing;
an RF receiver located within the housing, wherein the housing is configured to be positioned such that a field of view of the RF receiver is pointed toward a monitored region that includes a user in bed;
a radar processing circuit located within the housing that processes data received from the RF receiver and outputs raw waveform data;
a processing system, comprising one or more processors, that is in communication with the radar processing circuit, the processing system being configured to:
receive the raw waveform data from the radar processing circuit;
filter, from the raw waveform data, waveform data indicative of static objects to obtain motion-indicative waveform data;
analyze the motion-indicative waveform data to determine one or more frequencies of movement present within the motion-indicative waveform data;
determine one or more vital signs of the user present within the monitored region based on analyzing the motion-indicative waveform data;
perform, using a trained machine learning arrangement, a classification based on multiple spectral characteristics of, the motion-indicative waveform data to determine a state of the monitored region, wherein:
the trained machine learning arrangement is trained using a set of training data in which the training data is classified as mapping the multiple spectral characteristics to ground-truth user states; and
the trained learning arrangement classifies into a plurality of states, comprising a first state in which the user is present and is performing vitals-only movement, a second state in which the user is present and moving, and a third state in which the user is not present;
determine whether vital sign monitoring is permitted based on the state of the monitored region being in the first state in which the user is present and is performing vitals-only movement; and
in response to determining that vital sign monitoring is permitted based on the monitored region being in the first state, output the one or more determined vital signs of the user.