Determining a time period a person is in bed

Patent metadata

Field	Value
Publication number	US-10324109-B2
Application number	US-201615265902-A
Country	US
Kind code	B2
Filing date	Sep 15, 2016
Priority date	Jul 12, 2012
Publication date	Jun 18, 2019
Grant date	Jun 18, 2019

Abstract

A method and wireless sensor device for determining a time period a person is in bed. In one aspect, a method includes utilizing a wireless sensor device to obtain a plurality of acceleration samples in relation to at least one axis associated with a person's body over a predetermined time window. The method also includes calculating a polar angle for each acceleration sample within the predetermined time window. The method also includes calculating a fraction of an amount of time within the predetermined time window that the polar angle is greater than an angle threshold that indicates that the person is lying down, where if the fraction is greater than a predetermined threshold, the predetermined time window is marked as a period the person is lying down.

First claim

What is claimed is:

1. A computer-implemented method to determine sleep patterns, comprising:
measuring, by a sensor of a wireless sensor device mounted on at least one of: a chest, torso, or thorax of a user, a first plurality of acceleration samples and a second plurality of acceleration samples;
storing the first and second plurality of acceleration samples in a memory of the wireless sensor device;
implementing an application coupled to the memory storing the first and second plurality of acceleration samples and determining a first and second bed entry data and a first and second bed exit data for a first and second bed period, respectively, by:
utilizing the first and second plurality of acceleration samples in relation to at least one axis associated with a person's body over a first and second predetermined time window, respectively,
wherein the first and second plurality of acceleration samples are calibrated by a calibration procedure of the application that enables generation of at least one derived axis of acceleration data that lines up with the at least one axis associated with the person's body, and
wherein the first and second plurality of acceleration samples measure a first and second plurality of sleep parameters, respectively,

calculating a polar angle for each acceleration sample of the first and second plurality of acceleration samples within the first and second predetermined time window,
calculating a fraction of an amount of time within the first and second predetermined time window that the polar angle is greater than an angle threshold that indicates that the person is lying down, wherein in response to the fraction being greater than a predetermined angle threshold, the first and second predetermined time window are marked as a period the person is lying down,
triggering a start of a first and second sleep algorithm by using the first and second plurality of sleep parameters measured in the first and second plurality of acceleration samples, respectively,
determining the first bed entry data and the first bed exit data for the first bed period using the first sleep algorithm,
determining the second bed entry data and the second bed exit data for the second bed period using the second sleep algorithm,
determining whether a period of time between the first bed exit data and the second bed entry data is greater than a maximum out-of-bed period,
in response to a determination that the period of time between the first bed exit data and the second bed entry data is less than a maximum out-of-bed period:
combining the first bed period and the second bed period to determine a time period a person is in bed,
triggering an end of the first and second sleep algorithm to complete the first and second sleep algorithm by using the first and second plurality of sleep parameters measured in the first and second plurality of acceleration samples, and
determining sleep patterns using the completed first and second sleep algorithm.

2. The method of claim 1 , further comprising in response to the determination that the period of time between the first bed exit data and the second bed entry data is less than a maximum out-of-bed period, setting, by the wireless sensor device, the second bed entry as the first bed entry which removes the first bed period.

3. The method of claim 1 , wherein the at least one axis includes a plurality of axes in relation to the person's body.

4. The method of claim 1 , wherein the at least one axis includes one or more of an X-axis, a Y-axis, and a Z-axis in relation to the person's body.

5. The method of claim 1 , wherein the at least one axis includes an X-axis, a Y-axis, and a Z-axis.

6. The method of claim 1 , wherein the at least one axis includes a mediolateral axis, a vertical axis, and an anteroposterior axis.

7. The method of claim 1 , wherein the wireless sensor device is at least one of a triaxial accelerometer, a uni-axial accelerometers, a bi-axial accelerometers, a gyroscope, and a pressure sensor.

8. A wireless sensor device that determines a time period a person is in bed for determining sleep patterns, comprising: a sensor, mounted on at least one of: a chest, torso, or thorax of a user, that measures a first plurality of acceleration samples and a second plurality of acceleration samples;
a memory that stores the first and second plurality of acceleration samples;
a processor; and
an application coupled to the memory device, wherein the application, when executed by the processor, causes the processor to determine a first and second bed entry data and a first and second bed exit data for a first and second bed period by performing operations comprising:
utilizing the first and second plurality of acceleration samples in relation to at least one axis associated with a person's body over a first and second predetermined time window, respectively,
wherein the first and second plurality of acceleration samples are calibrated by a calibration procedure of the wireless sensor device that enables generation of at least one derived axis of acceleration data that ones up with the at least one axis associated with the person's body, and wherein the first and second plurality of acceleration samples measure a first and second plurality of sleep parameters, respectively,
calculating a polar angle for each acceleration sample of the first and second plurality of acceleration samples within the first and second predetermined time window,
calculating a fraction of an amount of time within the first and second predetermined time window that the polar angle is greater than an angle threshold that indicates that the person is lying down, wherein in response to the fraction being greater than a predetermined angle threshold, the first and second predetermined time window mare marked as a period the person is lying down,
triggering a start of a first and second sleep algorithm by using the first and second plurality of sleep parameters measured in the first and second plurality of acceleration samples, respectively
determining the first bed entry data and the first bed exit data for the first bed period using the first sleep algorithm,
determining the second bed entry data and the second bed exit data for the second bed period using the second sleep algorithm,
determining whether a period of time between the first bed exit data and the second bed entry data is less than a maximum out-of-bed period,
in response to a determination that the period of time between the first bed exit data and the second bed entry data is less than a maximum out-of-bed period:
combining the first bed period and the second bed period to determine a time period a person is in bed, and triggering an end of the first and second sleep algorithm to complete the first and second sleep algorithm by using the first and second plurality of sleep parameters measured in the first and second plurality of acceleration samples and
determining sleep patterns using the completed first and second sleep algorithm.

9. The wireless sensor device of claim 8 , further comprising in response to the determination that the period of time between the first bed exit data and the second bed entry data is less than a maximum out-of-bed period, setting the second bed entry as the first bed entry which removes the first bed period.

10. The wireless sensor device of claim 8 , wherein the at least one axis includes a mediolateral axis, a vertical axis, and an anteroposterior axis.

Assignees

• Vital Connect Inc

Inventors

• Chan Alexander
• Narasimhan Ravi

Classifications

• G01P15/00

  Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration · CPC title

• G07C1/00

  Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people (registering or indicating the working of machines or vehicles G07C3/00, G07C5/00) · CPC title

• A61B2560/0223

  of calibration, e.g. protocols for calibrating sensors · CPC title

• G06F19/00

  Physics · mapped topic

• A61B5/11

  Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb {(A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721)} · CPC title