Performance of biological measurements in the presence of noise
First Claim
Patent Images
1. A method for determining a heart-rate variability (HRV) measurement of a user, comprising:
- receiving, from a sensor of an electronic device of the user, heart sensor data;
determining, based on the received heart sensor data, an initial HRV measurement of the user;
determining in real-time, using a noise model for the HRV of the user, a noise level of the received heart sensor data, wherein the noise model is based on post-hoc analysis of one or more previous HRV measurements of the user;
adjusting the initial HRV measurement by an amount calculated based on the determined noise level; and
providing the initial HRV measurement to a database of HRV measurements associated with the noise model.
1 Assignment
0 Petitions
Accused Products
Abstract
In particular embodiments, a method for determining a heart-rate variability (HRV) measurement of a user may include receiving, from a sensor of an electronic device of the user, heart sensor data, determining a noise level of the heart sensor data, and then adjusting the HRV measurement by an amount calculated based on the determined noise level. The sensor data may include data on a photoplethysmograph (PPG) signal over a noise-calculation time period.
-
Citations
13 Claims
-
1. A method for determining a heart-rate variability (HRV) measurement of a user, comprising:
-
receiving, from a sensor of an electronic device of the user, heart sensor data; determining, based on the received heart sensor data, an initial HRV measurement of the user; determining in real-time, using a noise model for the HRV of the user, a noise level of the received heart sensor data, wherein the noise model is based on post-hoc analysis of one or more previous HRV measurements of the user; adjusting the initial HRV measurement by an amount calculated based on the determined noise level; and providing the initial HRV measurement to a database of HRV measurements associated with the noise model. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. One or more computer-readable non-transitory storage media embodying software for determining a heart-rate variability (HRV) measurement of a user that is operable when executed to:
-
receive, from a sensor of an electronic device of the user, heart sensor data; determine, based on the received heart sensor data, an initial HRV measurement of the user; determine in real-time, using a noise model for the HRV of the user, a noise level of the received heart sensor data, wherein the noise model is based on post-hoc analysis of one or more previous HRV measurements of the user; adjust the initial HRV measurement by an amount calculated based on the determined noise level; and provide the initial HRV measurement to a database of HRV measurements associated with the noise model.
-
-
8. A system comprising:
- one or more processors; and
a non-transitory memory coupled to the processors comprising instructions for determining a heart-rate variability (HRV) measurement of a user executable by the processors, the processors operable when executing the instructions to;receive, from a sensor of an electronic device of the user, heart sensor data; determine, based on the received heart sensor data, an initial HRV measurement of the user; determine in real-time, using a noise model for the HRV of the user, a noise level of the received heart sensor data, wherein the noise model is based on post-hoc analysis of one or more previous HRV measurements of the user; adjust the initial HRV measurement by an amount calculated based on the determined noise level; and provide the initial HRV measurement to a database of HRV measurements associated with the noise model.
- one or more processors; and
-
9. A method for measuring heart rate, comprising:
-
receiving, from a sensor of an electronic device of a user, heart sensor data of a user; analyzing in real-time, using a noise model for the heart sensor data, an amount of noise at one or more predetermined features of the heart sensor data to determine whether the one or more features have been corrupted by noise, wherein the noise model is based on post-hoc analysis of previous heart sensor data of the user; and computing RR intervals of the heart rate based on one or more of the features that are determined to not have been corrupted by noise. - View Dependent Claims (10, 11, 12, 13)
-
Specification