Automatic detection of user's periods of sleep and sleep stage

• US 10,772,539 B2
• Filed: 08/08/2018
• Issued: 09/15/2020
• Est. Priority Date: 09/23/2014
• Status: Active Grant

• Current Assignee: Fitbit, Inc. (Alphabet Inc.)
• Original Assignee: Fitbit, Inc. (Alphabet Inc.)
• Inventors: Arnold, Jacob Antony, Venkatraman, Subramaniam
• Primary Examiner(s): Abouelela, May A
• Application Number:
  US16/058,423
• Publication Number:
  US 20190038185A1
• Time in Patent Office: 769 Days
• Field of Search: 600300, 600301, 600587, 600595, 702104
• CPC Class Codes: A61B 2560/0209 adapted for power saving
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 2562/04 Arrangements of multiple sensors of the same type
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/0533 Measuring galvanic skin response
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/1122 of movement trajectories
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/4809 Sleep detection, i.e. determining whether a subject is asleep or not
• CPC Class Codes: A61B 5/4812 Detecting sleep stages or cycles
• CPC Class Codes: A61B 5/6801 specially adapted to be attached to or worn on the body surface
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7278 : Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: A61B 5/743 : Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots

Abstract

Aspects of automatically detecting periods of sleep of a user of a wearable electronic device are discussed herein. For example, in one aspect, an embodiment may obtain a set of features for periods of time from motion data obtained from a set of one or more motion sensors in the wearable electronic device or data derived therefrom. The wearable electronic device may then classify the periods of time into one of a plurality of statuses of the user based on the set of features determined for the periods of time, where the statuses are indicative of relative degree of movement of the user. The wearable electronic device may also derive blocks of time each covering one or more of the periods of time during which the user is in one of a plurality of states, wherein the states include an awake state and an asleep state.

Claims

1. A wearable electronic device, comprising:

one or more biometric sensors configured to generate biometric data;

one or more processors coupled to the one or more biometric sensors; and

a non-transitory machine-readable storage medium coupled to the one or more processors and having stored therein instructions which, when executed by the one or more processors, cause the one or more processors to;

receive the biometric data from the one or more biometric sensors,

determine a plurality of statistical feature values based on the biometric data generated by the one or more biometric sensors,

determine an activity level for each period of time of a plurality of periods of time based on the determined statistical feature values, wherein the activity level for each period of time is either active or inactive,

classify each period of time of the periods of time that has an activity level of active into one of a plurality of sleep states based at least on the activity level for at least two periods of time of the periods of time, wherein the plurality of sleep states includes an awake state and an asleep state,

classify each period of time of the periods of time that has an activity level of inactive into one of the plurality of sleep states based at least on the activity level for at least two periods of time of the periods of time, and

present information based on the sleep state classifications for the periods of time.

2. The wearable electronic device of claim 1, wherein:

the one or more biometric sensors comprise one or more motion sensors configured to generate motion data indicative of motion of the wearable electronic device, and

the instructions, when executed by the one or more processors, cause the one or more processors to determine at least some of the statistical features values by comparing a rolling fraction of the motion data to a threshold value.

3. The wearable electronic device of claim 1, wherein:

the one or more biometric sensors comprise one or more photoplethysmography (PPG) sensors configured to generate PPG data indicative of a heart rate of a user, and

the instructions, when executed by the one or more processors, cause the one or more processors to determine at least some of the statistical features values by determining a rolling median or a rolling average of the PPG data.

4. The wearable electronic device of claim 3, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

determine variabilities in inter-peak intervals between heart beats, and

determine at least some of the statistical features values by determining a number of times the variabilities in inter-peak intervals between heart beats exceeds a threshold.

5. The wearable electronic device of claim 3, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

determine the heart rate of the user based on the PPG data, and

determine at least some of the statistical features values based on the heart rate.

6. The wearable electronic device of claim 3, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

determine the heart rate of the user based on the PPG data,

determine that the heart rate of the user does not drop by a threshold value after onset of sleep, and

refrain from using the heart rate to determine the activity level for each period of time of the plurality of periods of time.

7. The wearable electronic device of claim 1, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

determine at least some of the statistical feature values by combining the biometric data received from at least one of the one or more biometric sensors over a time interval into a single numerical value.

8. The wearable electronic device of claim 1, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:

determine that the wearable electronic device is in a not-worn state during one or more additional periods of time based on the biometric data, and

classify the additional periods of time into one of the plurality of sleep states, wherein the plurality of sleep states includes the awake state and the asleep state, based at least on the activity level for at least two periods of time of the periods of time.

9. The wearable electronic device of claim 1, wherein the instructions, when executed by the one or more processors, cause the one or more processors to classify each period of time of the plurality of periods of time into one of the plurality of sleep states additionally based on the activity level determined for one or more items selected from the group consisting of:

one or more preceding time periods and one or more succeeding time periods.

10. A method executed by a wearable electronic device, the method comprising:

receiving, by one or more processors, biometric data from one or more biometric sensors configured to generate biometric data;

determining, by the one or more processors, a plurality of statistical feature values based on the biometric data generated by the one or more biometric sensors;

determining, by the one or more processors, an activity level for each period of time of a plurality of periods of time based on the plurality of statistical feature values determined therefor, wherein the activity level for each period of time of the periods of time is active or inactive;

classifying, by the one or more processors, each period of time of the periods of time that has an activity level of active into one of a plurality of sleep states based at least on the activity level for at least two periods of time of the periods of time, wherein the plurality of sleep states includes an awake state and an asleep state;

classifying, by the one or more processors, each period of time of the periods of time that has an activity level of inactive into one of the plurality of sleep states based at least on the activity level for at least two periods of time of the periods of time; and

presenting, by the one or more processors, information based on the sleep state classifications for the periods of time to a user.

11. The method of claim 10, wherein:

the one or more biometric sensors comprise one or more motion sensors configured to generate motion data indicative of motion of the wearable electronic device, and

the method further includes determining, by the one or more processors, at least some of the statistical feature values by comparing a rolling fraction of the motion data to a threshold value.

12. The method of claim 10, wherein:

the one or more biometric sensors comprise one or more photoplethysmography (PPG) sensors configured to generate PPG data indicative of a heart rate of the user, and

the method further includes determining, by the one or more processors, at least some of the statistical feature values by determining a rolling median or a rolling average of the PPG data.

13. The method of claim 12, further comprising:

determining, by the one or more processors, variabilities in inter-peak intervals between heart beats; and

determining, by the one or more processors, at least some of the statistical feature values by determining a number of times the variabilities in inter-peak intervals between heart beats exceeds a threshold.

14. The method of claim 12, further comprising:

determining, by the one or more processors, a heart rate of the user based on the PPG data; and

determining, by the one or more processors, at least some of the statistical feature values based on the heart rate.

15. The method of claim 12, further comprising:

determining, by the one or more processors, a heart rate of the user based on the PPG data;

determining, by the one or more processors, that the heart rate of the user does not drop by a threshold value after onset of sleep; and

refraining from using the heart rate to determine the activity level for each period of time of the plurality of periods of time.

16. A computer readable storage device that includes instructions which, when executed by one or more processors, cause the one or more processors to:

receive biometric data from one or more biometric sensors configured to generate biometric data;

determine a plurality of statistical feature values based on the biometric data generated by the one or more biometric sensors;

determine an activity level for each period of time of a plurality of periods of time based on the determined statistical feature values, wherein the activity level for each period of time is active or inactive;

classify each period of time of the periods of time that has an activity level of active into one of a plurality of sleep states, based at least on the activity level for at least two periods of time of the periods of time, wherein the plurality of sleep states includes an awake state and an asleep state;

classify each period of time of the periods of time that has an activity level of inactive into one of the plurality of sleep states, based at least on the activity level for at least two periods of time of the periods of time; and

present information based on the sleep state classifications for the periods of time to a user.

17. The computer readable storage device of claim 16, wherein:

the one or more biometric sensors comprise one or more motion sensors configured to generate motion data indicative of motion of a wearable electronic device, and

the instructions, when executed, cause the one or more processors to determine the statistical feature values by comparing a rolling fraction of the motion data to a threshold value.

18. The computer readable storage device of claim 16, wherein:

the one or more biometric sensors comprise one or more photoplethysmography (PPG) sensors configured to generate PPG data indicative of a heart rate of the user, and

the instructions, when executed, cause the one or more processors to determine at least some of the statistical feature values by determining a rolling median or a rolling average of the PPG data.

19. The computer readable storage device of claim 18, wherein the instructions, when executed, cause the one or more processors to:

determine variabilities in inter-peak intervals between heart beats; and

determine at least some of the statistical feature values by determining a number of times the variabilities in inter-peak intervals between heart beats exceeds a threshold.

20. The computer readable storage device of claim 18, wherein the instructions, when executed, cause the one or more processors to:

determine the heart rate of the user based on the PPG data; and

determine at least some of the statistical feature values based on the heart rate.