HEART RATE DETERMINATION IN POWER-CONSTRAINED ENVIRONMENT
Methods, systems, computer-readable media, and apparatuses for power-constrained heartbeat rate determination using a device physically coupled to a user are disclosed.
1 . A device, comprising:
a sensor coupled to a housing configured to be physically coupled to a user;
a controller coupled to the sensor, the controller configured to:
obtain a first characteristic vector that indicates a direction corresponding to movement induced by a heartbeat of the user;
obtain, from the sensor, while the housing is physically coupled to the user, a first dataset indicative of a movement of the sensor;
generate a second dataset based on the first characteristic vector and the first dataset; and
determine a heartbeat rate of the user based on a frequency domain analysis of the second dataset.
2 . The device of claim 1 , wherein the controller is further configured to:
obtain a second characteristic vector that indicates a direction corresponding to movement induced by breathing of the user;
generate a third dataset based on the second characteristic vector and the first dataset; and
determine a breathing rate of the user based on the third dataset.
3 . The device of claim 2 , wherein the third dataset includes the second dataset.
4 . The device of claim 2 , wherein the breathing rate of the user is not determined based on a frequency domain analysis.
5 . The device of claim 2 , wherein the first characteristic vector and the second characteristic vector are each obtained from a dataset acquired during a calibration cycle, wherein the dataset is compared to respective expected ranges of movements based on a comparison to a gravity vector, each of the expected ranges of movements corresponding respectively to a heartbeat of a user and a breathing rate of the user.
6 . The device of claim 1 , wherein the generating the second dataset includes performing a dot product multiplication of the first characteristic vector with the first dataset.
7 . The device of claim 1 , wherein the sensor includes at least one of a multi-axis accelerometer, multi-axis gyroscope, multi-axis magnetometer, multi-axis inertial measurement unit, or any combination thereof.
8 . The device of claim 1 , further comprising an adhesive configured to physically couple the housing to the user.
9 . The device of claim 1 , wherein the housing is configured to hermetically seal the controller from an external environment.
10 . The device of claim 1 , wherein the first characteristic vector is obtained during a calibration cycle wherein one or more detected movements are compared to an expected range of movements based on a comparison of the one or more detected movements to a gravity vector.
11 . The device of claim 1 , wherein generating the second dataset includes filtering the first dataset to reduce frequency components outside of an expected frequency range of the heartbeat rate of the user.
12 . The device of claim 1 , wherein the frequency domain analysis of the second dataset includes performing a Fast Fourier Transform on a frequency range expected to include the heartbeat rate of the user.
13 . The device of claim 1 , wherein the controller is configured to perform the frequency domain analysis of the second dataset.
14 . A method, comprising:
obtaining, by a controller, a first characteristic vector that indicates a direction corresponding to movement induced by a heartbeat of a user;
obtaining, by the controller, from a sensor physically coupled to a housing, while the housing is physically coupled to the user, a first dataset indicative of a movement of the sensor;
generating, by the controller, a second dataset based on the first characteristic vector and the first dataset; and
determining, by the controller a heartbeat rate of the user based on a frequency domain analysis of the second dataset.
15 . The method of claim 14 , further comprising:
obtaining, by the controller, a second characteristic vector that indicates a direction corresponding to movement induced by breathing of the user;
generating, by the controller, a third dataset based on the second characteristic vector and the first dataset; and
determining, by the controller a breathing rate of the user based on the third dataset.
16 . The method of claim 15 , wherein the third dataset includes the second dataset.
17 . The method of claim 15 , wherein the breathing rate of the user is not determined based on a frequency domain analysis.
18 . The method of claim 15 , wherein the first characteristic vector and the second characteristic vector are both obtained from one dataset acquired during a calibration cycle, wherein the dataset is compared to respective expected ranges of movements based on a comparison to a gravity vector, each of the expected ranges of movements corresponding respectively to a heartbeat of a user and a breathing rate of the user.
19 . The method of claim 14 , wherein the generating the second dataset includes performing a dot product multiplication of the first characteristic vector with the first dataset.
20 . An apparatus, comprising:
a means for obtaining a first characteristic vector that indicates a direction corresponding to movement induced by a heartbeat of a user;
a means for obtaining, from a sensor physically coupled to a housing, while the housing is physically coupled to the user, a first dataset indicative of a movement of the means for sampling;
a means for generating a second dataset based on the first characteristic vector and the first dataset; and
a means for determining a heartbeat rate of the user based on results of a frequency domain analysis of the second dataset.
21 . The apparatus of claim 20 , further comprising:
a means for obtaining a second characteristic vector that indicates a direction corresponding to movement induced by breathing of the user;
a means for generating a third dataset based on the second characteristic vector and the first dataset; and
a means for determining a breathing rate of the user based on the third dataset.
22 . The apparatus of claim 21 , wherein the third dataset includes the second dataset.
23 . The apparatus of claim 21 , wherein the breathing rate of the user is not determined based on a frequency domain analysis.
24 . The apparatus of claim 21 , wherein the first characteristic vector and the second characteristic vector are both obtained from one dataset acquired during a calibration cycle, wherein the dataset is compared to respective expected ranges of movements based on a comparison to a gravity vector, each of the expected ranges of movements corresponding respectively to a heartbeat of a user and a breathing rate of the user.
25 . The apparatus of claim 20 , wherein the generating the second dataset includes performing a dot product multiplication of the first characteristic vector with the first dataset.
26 . One or more computer readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to:
obtain a first characteristic vector that indicates a direction corresponding to movement induced by a heartbeat of a user;
obtain, from a sensor physically coupled to a housing, while the housing is physically coupled to the user, a first dataset indicative of a movement of the sensor;
generate a second dataset based on the first characteristic vector and the first dataset; and
determine a heartbeat rate of the user based on frequency domain analysis of the second dataset.
27 . The one or more computer readable medium of claim 26 , further comprising instructions that, when executed by the one or more processors, cause the one or more processors to:
obtain a second characteristic vector that indicates a direction corresponding to movement induced by breathing of the user;
generate a third dataset based on the second characteristic vector and the first dataset; and
determine a breathing rate of the user based on the third dataset.
28 . The one or more computer readable medium of claim 27 , wherein the third includes the second dataset.
29 . The one or more computer readable medium of claim 27 , wherein the breathing rate of the user is not determined based on a frequency domain analysis.
30 . The one or more computer readable medium of claim 27 , wherein the first characteristic vector and the second characteristic vector are both obtained from one dataset acquired during a calibration cycle, wherein the dataset is compared to respective expected ranges of movements based on a comparison to a gravity vector, each of the expected ranges of movements corresponding respectively to a heartbeat of a user and a breathing rate of the user.