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

• US 10,092,219 B2
• Filed: 10/07/2015
• Issued: 10/09/2018
• 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:
  US14/877,912
• Publication Number:
  US 20160022203A1
• Time in Patent Office: 1,098 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. An apparatus for automatically detecting periods of sleep of a user of a wearable electronic device, the apparatus comprising:

one or more processors; 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;

obtain motion data from one or more motion sensors in the wearable electronic device,

define a plurality of time windows including a first time window and a second time window, the first and second time windows overlapping,

obtain a set of feature values from the motion data including a first feature value corresponding to a first time interval and determined based on the motion data within the first time window and a second feature value corresponding to a second time interval and determine based on the motion data within the second time window, the first time window comprising the first time interval and the second time interval, the second time interval being adjacent to the first time interval, and the second time window comprising the second time interval,

classify each of the time intervals into one of a plurality of statuses of the user based on the corresponding feature value, wherein the statuses are indicative of relative degrees of movement of the user,

consolidate one or more consecutive time intervals into one or more blocks of time based at least in part on the statuses corresponding to the one or more consecutive time intervals, wherein each block of time is indicative of the user being in one of an awake state and an asleep state, and

detect the periods of sleep of the user based on the consolidated blocks of time.

2. The apparatus of claim 1, wherein the classification is performed using a machine learning classifier.

3. The apparatus of claim 1, wherein the plurality of statuses further include a not-worn status, during which the user is not wearing the wearable electronic device.

4. The apparatus of claim 1, wherein the apparatus is one of the wearable electronic device and a secondary electronic device to be coupled to the wearable electronic device.

5. The apparatus of claim 1, wherein one of the feature values is based on a combination of a quantification of a distribution of motion data along each of three axes for one of the time intervals.

6. The apparatus of claim 1, wherein the classification of the first time intervals is further based on photoplethysmography (PPG) data from the first time window, and wherein the PPG data is generated by a photoplethysmographic sensor in the wearable electronic device.

7. The apparatus of claim 6, wherein the PPG data is utilized to calculate at least one of the user'"'"'s:

heart rate data;

heart rate variability data; and

respiration data.

8. The apparatus of claim 1, wherein the instructions, when executed by the one or more processors, also cause the one or more processors further to:

after the consolidation of at least one block of time indicating that the user is in the asleep state, determine, for the time intervals in the at least one block of time indicating that the user is in the asleep state, another set of statistical feature values of which at least one characterizes a distribution of movement of the user, and

classify each of the time intervals, during which the user is in the asleep state, into one of a plurality of sleep stages of the user based on the another set of statistical feature values, wherein the sleep stages include a rapid eye movement (REM) stage and a plurality of non-REM stages.

9. The apparatus of claim 1, wherein the classification of each of the time intervals is further based on data generated by one or more additional sensors in the wearable electronic device, wherein the one or more additional sensors include one or more of the following:

temperature sensor;

ambient light sensor;

galvanic skin response sensor;

capacitive sensor;

humidity sensor; and

sound sensor.

10. The apparatus of claim 1, wherein the one or more motion sensors include an accelerometer.

11. The apparatus of claim 1, wherein the non-transitory machine readable storage medium further has stored therein instructions, which when executed by the one or more processors, cause the one or more processors to communicate the detected periods of sleep of the user to a display for presentation to the user.

12. A method for automatically detecting periods of sleep of a user of a wearable electronic device, the wearable device comprising one or more processors, the method comprising:

obtaining, using the one or more processors of the wearable device, motion data from one or more motion sensors in the wearable electronic device;

defining, using the one or more processors of the wearable device, a plurality of time windows including a first time window and a second time window, the first and second time windows overlapping;

obtaining, using the one or more processors of the wearable device, a set of feature values from the motion data including a first feature value corresponding to a first time interval and determined based on the motion data within the first time window and a second feature value corresponding to a second time interval and determine based on the motion data within the second time window, wherein the first time window comprising the first time interval and the second time interval, the second time interval being adjacent to the first time interval, and the second time window comprising the second time interval;

classifying, using the one or more processors of the wearable device, each of the time intervals into one of a plurality of statuses of the user based on the corresponding feature value, wherein the statuses are indicative of relative degrees of movement of the user;

consolidating, using the one or more processors of the wearable device, one or more consecutive time intervals into one or more blocks of time based at least in part on the statuses corresponding to the one or more consecutive time intervals, wherein each block of time is indicative of the user being in one of an awake state and an asleep state; and

detecting, using the one or more processors of the wearable device, the periods of sleep of the user based on the consolidated blocks of time.

13. The method of claim 12, wherein the classifying is performed using a machine learning classifier.

14. The method of claim 12, wherein the plurality of statuses further include a not-worn status, during which the user is not wearing the wearable electronic device.

15. The method of claim 12, wherein the method is performed by one of the wearable electronic device and a secondary electronic device to be coupled to the wearable electronic device.

16. The method of claim 12, wherein one of the feature values is based on a combination of a quantification of a distribution of motion data along each of three axes for the time intervals.

17. The method of claim 12, wherein the classifying of the first time intervals is further based on photoplethysmography (PPG) data from the first time window, and wherein the PPG data is generated by a photoplethysmographic sensor in the wearable electronic device.

18. The method of claim 17, wherein the PPG data is utilized to calculate at least one of the user'"'"'s:

heart rate data;

heart rate variability data; and

respiration data.

19. The method of claim 12, further comprising:

after the consolidation of at least one block of time indicating that the user is in the asleep state, determining, using the one or more processor, for the time intervals in the at least one block of time indicating that the user is in the asleep state, another set of statistical feature values of which at least one characterizes a distribution of movement of the user, and

classifying, using the one or more processors, each of the time intervals, during which the user is in the asleep state, into one of a plurality of sleep stages of the user based on the another set of statistical feature values, wherein the sleep stages include a rapid eye movement (REM) stage and a plurality of non-REM stages.

20. The method of claim 12, wherein the classifying of each of the time intervals is further based on data generated by one or more additional sensors in the wearable electronic device, wherein the one or more additional sensors include one or more of the following:

temperature sensor;

ambient light sensor;

galvanic skin response sensor;

capacitive sensor;

humidity sensor; and

sound sensor.

21. The method of claim 12, wherein the one or more motion sensors include an accelerometer.

22. A computer readable storage device that includes instructions that are for automatically detecting periods of sleep of a user of a wearable electronic device and that, when executed by one or more processors, cause the one or more processors to:

obtain motion data from one or more motion sensors in the wearable electronic device;

define a plurality of time windows including a first time window and a second time window, the first and second time windows overlapping;

obtain a set of feature values from the motion data including a first feature value corresponding to a first time interval and determined based on the motion data within the first time window and a second feature value corresponding to a second time interval and determine based on the motion data within the second time window, the first time window comprising the first time interval and the second time interval, the second time interval being adjacent to the first time interval, and the second time window comprising the second time interval;

classify each of the time intervals into one of a plurality of statuses of the user based on the corresponding feature value, wherein the statuses are indicative of relative degrees of movement of the user;

consolidate one or more consecutive time intervals into one or more blocks of time based at least in part on the statuses corresponding to the one or more consecutive time intervals, wherein each block of time is indicative of the user being in one of an awake state and an asleep state; and

detect the periods of sleep of the user based on the consolidated blocks of time.

23. The computer readable storage device of claim 22, wherein the classification is performed using a machine learning classifier.

24. The computer readable storage device of claim 22, wherein the plurality of statuses further include a not-worn status, during which the user is not wearing the wearable electronic device.

25. The computer readable storage device of claim 22, wherein the computer readable storage device is in one of the wearable electronic device and a secondary electronic device to be coupled to the wearable electronic device.

26. The computer readable storage device of claim 22, wherein one of the feature values is based on a combination of a quantification of a distribution of motion data along each of three axes for one of the time intervals.

27. The computer readable storage device of claim 22, wherein the classification of the first time intervals is further based on photoplethysmography (PPG) data from the first time window, and wherein the PPG data is generated by a photoplethysmographic sensor in the wearable electronic device.

28. The computer readable storage device of claim 27, wherein the PPG data is utilized to calculate at least one of the user'"'"'s:

heart rate data;

heart rate variability data; and

respiration data.

29. The computer readable storage device of claim 22, wherein the instructions, when executed by the one or more processors, also cause the one or more processors further to:

after the consolidation of at least one block of time indicating that the user is in the asleep state, determine, for the time intervals in the at least one block of time indicating that the user is in the asleep state, another set of statistical feature values of which at least one characterizes a distribution of movement of the user, and

classify each of the time intervals, during which the user is in an asleep state, into one of a plurality of sleep stages of the user based on the another set of statistical feature values, wherein the sleep stages include a rapid eye movement (REM) stage and a plurality of non-REM stages.

30. The computer readable storage device of claim 22, wherein the classification of each of the time intervals is further based on data generated by one or more additional sensors in the wearable electronic device, wherein the one or more additional sensors include one or more of the following:

temperature sensor;

ambient light sensor;

galvanic skin response sensor;

capacitive sensor;

humidity sensor; and

sound sensor.

31. The computer readable storage device of claim 22, wherein the one or more motion sensors include an accelerometer.