Method and apparatus for identifying transitions between sitting and standing postures

• US 9,934,668 B2
• Filed: 11/29/2013
• Issued: 04/03/2018
• Est. Priority Date: 11/30/2012
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke NV
• Inventors: Zhang, Wei, Wahle, Fabian-Felix
• Primary Examiner(s): Lu, Shirley
• Application Number:
  US14/646,404
• Publication Number:
  US 20150302720A1
• Time in Patent Office: 1,586 Days
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/6822 Neck
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G08B 21/0446 worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait

Abstract

There is provided a method for identifying transitions between a standing posture and a sitting posture by a user, the method comprising obtaining measurements of the acceleration experienced by the user during movement; obtaining a signal indicating the height of a part of the user during movement; processing the measurements of the acceleration to identify candidate movements corresponding to transitions between a standing posture and a sitting posture; and determining an identified candidate movement as a transition from a sitting posture to a standing posture where the identified candidate movement coincides with an increase in height in the signal and an identified candidate movement as a transition from a standing posture to a sitting posture where the identified candidate movement coincides with a decrease in height in the signal.

Claims

1. A method for identifying transitions between a standing posture and a sitting posture by a user, the method comprising:

measuring, with an accelerometer, an acceleration experienced by the user during movement and outputting measurements of the acceleration;

measuring, with a sensor, a height of a part of the user during movement and outputting a signal indicating the height;

processing, with a hardware processor, the measurements of the acceleration to identify candidate movements corresponding to transitions between a standing posture and a sitting posture; and

determining, with the hardware processor, an identified candidate movement as a transition from a sitting posture to a standing posture where the identified candidate movement coincides with an increase in the height in the signal and an identified candidate movement as a transition from a standing posture to a sitting posture where the identified candidate movement coincides with a decrease in the height in the signal.

2. The method as claimed in claim 1, wherein the step of processing the measurements of the acceleration to identify candidate movements corresponding to transitions between a standing posture and a sitting posture comprises matching the measurements of the acceleration to a predetermined acceleration profile for a sit-to-stand transfer.

3. The method as claimed in claim 2, wherein the step of matching the measurements of the acceleration to a predetermined acceleration profile for a sit-to-stand transfer comprises:

filtering the measurements of acceleration with the predetermined acceleration profile to produce a forward-filtered signal;

reversing the forward-filtered signal; and

filtering the reversed signal with the predetermined acceleration profile.

4. The method as claimed in claim 2, wherein the step of processing the measurements of the acceleration further comprises filtering the signal resulting from the step of matching with a filter that enhances the magnitude of the parts of the signal that correspond to sit-to-stand and stand-to-sit transfers and that suppresses the magnitude of the parts of the signal that correspond to the user walking.

5. The method as claimed in claim 4, wherein the step of filtering comprises:

(a) for a subset of samples in a window on the signal resulting from the step of matching;

(i) determining the average of the samples in the subset;

(ii) subtracting the determined average from each of the samples in the subset;

(iii) determining the absolute value of each sample in the output of step (ii);

(iv) determining the average of the samples in the output of step (iii);

(b) moving the window across the signal resulting from the step of matching and repeating step (a);

(c) determining the moving average of the signal obtained in step (b) to produce a filtered signal;

or wherein the step of filtering comprises;

(a) for a subset of samples in a window on the signal resulting from the step of matching;

(i) subtracting a value from each of the samples in the subset;

(ii) determining the absolute value of each sample in the output of step (i);

(iii) determining the average of the samples in the output of step (ii);

(b) moving the window across the signal resulting from the step of matching and repeating step (a); and

(c) determining the moving average of the signal obtained in step (b) to produce a filtered signal.

6. The method as claimed in claim 4, wherein the step of processing the measurements of the acceleration further comprises:

identifying candidate movements in the filtered signal as the peaks in the filtered signal.

7. The method as claimed in claim 6, wherein a candidate movement is identified where the peak has a magnitude greater than a threshold value.

8. The method as claimed in claim 7, wherein the step of processing the measurements of the acceleration to identify candidate movements corresponding to transitions between a standing posture and a sitting posture further comprises:

estimating the start and end times for each identified candidate movement as the times corresponding to the samples either side of the corresponding peak in the filtered signal where the magnitude of the samples are equal to a predetermined proportion of the threshold value.

9. The method as claimed in claim 8, further comprising the step of determining the change in height for each candidate movement from the obtained height signal by:

determining the height before the candidate movement as the average of the height of the part of the user over a window covering samples in the height signal before the estimated start time for the candidate movement;

determining the height after the candidate movement as the average of the height of the part of the user over a window covering samples in the height signal after the estimated end time for the candidate movement; and

subtracting the determined height before the candidate movement from the determined height before the candidate movement to give the change in height during the candidate movement.

10. The method as claimed in claim 8, further comprising:

determining when the user is on their feet as the time periods following a transition from a sitting posture to a standing posture until the next transition from a standing posture to a sitting posture; and

summing the duration of each of the time periods to give the time-on-leg.

11. The method according to claim 10, the method further comprising:

determining a risk of falling for the user from the determined time-on-leg.

12. A non-transitory computer readable medium, comprising computer program code that, when executed on a computer, causes the computer to identify transitions between a standing posture and a sitting posture in measurements of the movement of a user by:

obtaining measurements of an acceleration experienced by the user during movement;

obtaining a signal indicating a height of a part of the user during movement;

processing the measurements of the acceleration to identify candidate movements corresponding to transitions between a standing posture and a sitting posture; and

determining an identified candidate movement as a transition from a sitting posture to a standing posture where the identified candidate movement coincides with an increase in the height in the signal and an identified candidate movement as a transition from a standing posture to a sitting posture where the identified candidate movement coincides with a decrease in the height in the signal.

13. An apparatus for identifying transitions between a standing posture and a sitting posture in measurements of the movement of a user, the apparatus comprising:

a hardware processor configured to;

process measurements of an acceleration experienced by the user to identify candidate movements corresponding to transitions between a standing posture and a sitting posture; and

determine an identified candidate movement as a transition from a sitting posture to a standing posture where the identified candidate movement coincides with an increase in a height in a signal indicating a height of a part of the user during movement, and determine an identified candidate movement as a transition from a standing posture to a sitting posture where the identified candidate movement coincides with a decrease in the height in the signal indicating the height of the part of the user.

14. The apparatus as claimed in claim 13 further comprising:

an accelerometer that measures an acceleration acting on the device in three dimensions, wherein the processing unit is configured to process the measurements of the acceleration from the accelerometer.

15. The apparatus as claimed in claim 13, further comprising:

a device that is configured to be worn by a user, the device comprising an accelerometer that measures an acceleration acting on the device in three-dimensions; and

a base unit that is configured to communicate with the device, wherein the processing unit is configured to process the measurements of the acceleration from the accelerometer.