Movement measure generation in a wearable electronic device

• US 9,808,185 B2
• Filed: 09/18/2015
• Issued: 11/07/2017
• 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): EISEMAN, ADAM JARED
• Application Number:
  US14/859,192
• Publication Number:
  US 20160007934A1
• Time in Patent Office: 781 Days
• 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 generating movement measures that quantify motion data samples generated by a wearable electronic device are discussed herein. For example, in one aspect, an embodiment may obtain motion data samples generated by the set of motion sensors in a wearable electronic device. The wearable electronic device may then generate a first movement measure based on a quantification of the first set of motion data samples. The wearable electronic device may also generate a second movement measure based on a quantification of the second set of the motion data samples. The wearable electronic device may then cause the non-transitory machine readable storage medium to store the first movement measure and the second movement measure as time series data.

Claims

1. A wearable electronic device to be worn by a user, the wearable electronic device comprising:

a set of one or more motion sensors to generate motion data samples that represent motion of the wearable electronic device, the motion data samples include a plurality of first motion data samples generated during a first time interval and a plurality of second motion data samples generated during a second time interval;

a set of one or more processors coupled to the set of motion sensors; and

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

obtain the motion data samples generated by the set of motion sensors,

generate a first movement measure based on a combination of the first motion data samples into a single numerical value representative of the motion of the wearable electronic device during the first time interval,

generate a second movement measure based on a combination of the second motion data samples into a single numerical value representative of the motion of the wearable electronic device during the second time interval,

cause the non-transitory machine readable storage medium to store the first movement measure and the second movement measure as time series data,

derive a first feature value corresponding to the first time interval based on the single numerical values of the first and second movement measures,

derive a second feature value corresponding to the second time interval based on at least the single numerical value of the second movement measure,

assign a first sleep state to the user of the wearable electronic device for the first time interval based on the first feature value, and

assign a second sleep state to the user of the wearable electronic device for the second time interval based on the second feature value.

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

determine levels of activity of the user for each of the first and second time intervals, wherein the determination of the level of activity for the first time interval is based on a comparison of the first feature value with a threshold value, and the levels of activity are used in the assigning of the sleep state.

3. The wearable electronic device of claim 1, wherein the generating of the first and second movement measures is based on a statistical measure of the corresponding motion data samples along an axis of motion of the set of one or more motion sensors.

4. The wearable electronic device of claim 3, wherein each of the statistical measures is one or more of a quantile, an inter-quantile range, a measure of dispersion, and a measure of entropy.

5. The wearable electronic device of claim 3, wherein each of the statistical measures is derived from a frequency domain analysis of the corresponding motion data samples.

6. The wearable electronic device of claim 5, wherein the frequency domain analysis quantifies an amount of periodic motion and compares the amount of periodic motion in two frequency bands.

7. The wearable electronic device of claim 1, wherein the generating of the first and second movements measures is based on a function of a maximum of the motion data and a minimum of the motion data along an axis.

8. The wearable electronic device of claim 7, wherein the function of the maximum motion data and the minimum motion data along the axis comprises application of a weighted value.

9. The wearable electronic device of claim 1, wherein the quantification of the motion data comprises a calculation of a standard deviation of the motion data along an axis.

10. The wearable electronic device of claim 1, wherein the quantification of the motion data comprises a calculation of a temporal derivative of the motion data along an axis.

11. The wearable electronic device of claim 1, wherein the quantification of the motion data comprises a combination of an inter-quantile range of the motion data along an axis.

12. The wearable electronic device of claim 1, wherein the assigning of the sleep state to the user of the wearable electronic device is further based on a plurality of movement measures located within a time window, the plurality of movement measures comprising at least the first and second movement measures, the time window including at least the first and second time intervals.

13. The wearable electronic device of claim 1, wherein the assigning of the sleep state to the user of the wearable electronic device comprises:

assigning a first sleep state to the user of the wearable electronic device for the first time interval based on a first time window including at least the first and second movement measures;

assigning a second sleep state to the user of the wearable electronic device for the second time interval based on a second time window that overlaps with the first time window and includes at least the second movement measure;

consolidating the first and second time intervals into the block of time in response to the first and second sleep states representing a same sleep state of the user.

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

obtaining a plurality of first motion data samples generated by a set of one or more motion sensors, the first motion data samples being generated during a first time interval;

generating a first movement measure based on a combination of the first motion data samples into a single numerical value representative of the motion of the wearable electronic device during the first time interval;

obtaining a plurality of second motion data samples generated by the set of motion sensors, the second motion data samples being generated during a second time interval;

generating a second movement measure based on a combination of the second the motion data samples into a single numerical value representative of the motion of the wearable electronic device during the second time interval;

causing a non-transitory machine readable storage medium to store the first movement measure and the second movement measure as time series data,

deriving a first feature value corresponding to the first time interval based on the single numerical values of the first and second movement measures;

deriving a second feature value corresponding to the second time interval based on at least the single numerical value of the second movement measure;

assigning a first sleep state to a user of the wearable electronic device for the first time interval based on the first feature value, and

assigning a second sleep state to the user of the wearable electronic device for the second time interval based on the second feature value.

15. The method of claim 14, further comprising:

determining levels of activity of the user for each of the first and second time intervals, wherein the determination of the level of activity for the first time interval is based on a comparison of the first feature value with a threshold value, and the levels of activity are used in the assigning of the sleep state.

16. The method of claim 14, wherein the generating of the first and second movement measures is based on a statistical measure of the corresponding motion data samples along an axis of motion of the set of one or more motion sensors.

17. The method of claim 16, wherein each of the statistical measures is one or more of a quantile, an inter-quantile range, a measure of dispersion, and a measure of entropy.

18. The method of claim 16, wherein each of the statistical measures is derived from a frequency domain analysis of the corresponding motion data samples.

19. The method of claim 18, wherein the frequency domain analysis quantifies an amount of periodic motion and compares the amount of periodic motion in two frequency bands.

20. The method of claim 14, wherein the generating of the first and second movements measures is based on a function of a maximum of the motion data and a minimum of the motion data along an axis.

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

obtain a first movement measure comprising a first single numerical value representative of motion of a wearable device during a first time interval, the first single numerical value being generated based on a combination of a plurality of first motion data samples generated by a set of one or more motion sensors of the wearable electronic device;

obtain a second movement measure comprising a second single numerical value representative of the motion of the wearable device during a second time interval, the second single numerical value being generated based on a combination of a plurality of second motion data samples generated by the motion sensors;

derive a first feature value corresponding to the first time interval based on the single numerical values of the first and second movement measures,

derive a second feature value corresponding to the second time interval based on at least the single numerical value of the second movement measure,

classify a first level of activity of the user for the first time interval based on the first feature value;

classify a second level of activity of the user for the second time interval based on the second feature value;

determine a sleep state for the first time interval based on the first level of activity; and

determine a sleep state for the second time interval based on the second level of activity.

22. The computer readable storage device of claim 21, wherein the instructions, when executed, cause the one or more processors to generate the first single numerical value based on an aggregation of multidimensional acceleration data over the first time interval.

23. The computer readable storage device of claim 21, wherein a device external to and physically separate from the wearable electronic device houses the one or more processors, and the instructions, when executed, cause the one or more processors to obtain the first movement measure and the second movement measure based on a reception of the first movement measure and the second movement measure from the wearable electronic device through a wireless connection.

24. The computer readable storage device of claim 21, wherein the block of time includes time intervals in addition to the first time interval, and the time intervals are classified using a mix of different levels of activity.