Posture calibration for activity monitoring

• US 9,035,794 B2
• Filed: 07/12/2012
• Issued: 05/19/2015
• Est. Priority Date: 07/12/2012
• Status: Active Grant

• Current Assignee: Vital Connect, Inc.
• Original Assignee: Vital Connect, Inc.
• Inventors: Narasimhan, Ravi, Ferdosi, Nima
• Primary Examiner(s): Wang, Jack K
• Application Number:
  US13/548,059
• Publication Number:
  US 20140015687A1
• Time in Patent Office: 1,041 Days
• Field of Search: 340/870.2, 702/19, 607/62, 345/419, 600/595
• US Class Current: 340/870.2
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: G01C 25/00 Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass testing, calibrating or compensating compasses G01C17/38
• CPC Class Codes: G01C 25/005 initial alignment, calibration or starting-up of inertial devices
• CPC Class Codes: G08C 17/02 using a radio link

Abstract

A method and system for activity monitoring of a user are disclosed. In a first aspect, the method comprises calibrating posture by the user to determine a calibration vector. The method includes validating the calibration vector by comparing an anteroposterior axis to a threshold, wherein activity of the user is monitored using the validated calibration vector. In a second aspect, a wireless sensor device comprises a processor and a memory device coupled to the processor, wherein the memory device includes an application that, when executed by the processor, causes the processor to receive a posture calibration request from the user and to determine a calibration vector based on the received request. The application, when executed by the processor, further causes the processor to validate the calibration vector by comparing an anteroposterior axis to a threshold, wherein activity of the user is monitored using the validated calibration vector.

Claims

1. A method for activity monitoring of a user, the method comprising:

calibrating posture by the user to determine a calibration vector; and

validating the calibration vector by comparing an anteroposterior axis to a threshold, wherein activity of the user is monitored by any of;

pedometer activity using a vertical component of an acceleration vector of the user;

fall detection using p-norm of an acceleration vector of the user to detect an impact and an angle of the acceleration vector with respect to the validated calibration vector thereby determining a horizontal position of the user after impact; and

posture detection using both an acceleration vector of the user and the validated calibration vector.

2. The method of claim 1, further comprising:

in response to a validation failure, monitoring the activity of the user independent of the calibration vector and reporting an unknown posture for the user; and

calibrating the posture implicitly when the user is walking.

3. The method of claim 2, further comprising:

in response to the validation failure, determining whether to recalibrate the posture explicitly.

4. The method of claim 1, wherein the validating further comprises:

ensuring a magnitude of acceleration along the anteroposterior axis is less than the threshold.

5. The method of claim 2, wherein the validation failure occurs when a magnitude of acceleration along the anteroposterior axis is greater than or equal to the threshold.

6. The method of claim 1, wherein calibrating the posture further comprises any of the user notifying a wireless sensor device when the user is in a vertical position and the user placing the wireless sensor device on the user'"'"'s chest when the user is in a vertical position.

7. The method of claim 6, wherein the notifying further comprises any of tapping of the wireless sensor device, selecting a button of the wireless sensor device, and interacting with a mobile application interface of the wireless sensor device.

8. The method of claim 6, further comprising:

in response to the placing, recognizing contact impedance to show attachment by the wireless sensor device.

9. The method of claim 2, wherein calibrating the posture implicitly further comprises deriving a vertical position by a wireless sensor device based on an acceleration vector corresponding to footsteps when the user is walking.

10. The method of claim 2, wherein the monitoring the activity of the user independent of the calibration vector further comprises any of:

monitoring pedometer activity using 2-norm of an acceleration vector of the user; and

monitoring fall detection using p-norm of the acceleration vector to detect an impact.

11. The method of claim 1, further comprising:

attaching a wireless sensor device to the user in any orientation and on any location.

12. The method of claim 1, further comprising:

relaying notification information of the activity monitoring of the user to another user or device.

13. A wireless sensor device for activity monitoring of a user, the wireless sensor device comprising:

a processor; and

a memory device coupled to the processor, wherein the memory device includes an application that, when executed by the processor, causes the processor to;

receive a posture calibration request from the user;

determine a calibration vector based on the received request; and

validate the calibration vector by comparing an anteroposterior axis to a threshold, wherein activity of the user is monitored by any of;

pedometer activity using a vertical component of an acceleration vector of the user;

fall detection using p-norm of an acceleration vector of the user to detect an impact and an angle of the acceleration vector with respect to the validated calibration vector thereby determining a horizontal position of the user after impact; and

posture detection using both an acceleration vector of the user and the validated calibration vector.

14. The wireless sensor device of claim 13, wherein the application, when executed by the processor, further causes the processor to:

in response to a validation failure, monitor the activity of the user independent of the calibration vector and report an unknown posture for the user; and

calibrate the posture implicitly when the user is walking.

15. The wireless sensor device of claim 13, wherein to validate further comprises to ensure a magnitude of acceleration along the anteroposterior axis is less than the threshold.

16. The wireless sensor device of claim 14, wherein the validation failure occurs when a magnitude of acceleration along the anteroposterior axis is greater than or equal to the threshold.

17. The wireless sensor device of claim 14, wherein to monitor the activity of the user independent of the calibration vector further comprises causing the processor to perform any of:

monitoring pedometer activity using 2-norm of an acceleration vector of the user; and

monitoring fall detection using p-norm of the acceleration vector to detect an impact.

18. The wireless sensor device of claim 13, wherein the application, when executed by the processor, further causes the processor to:

relay notification information of the activity monitoring of the user to another user or device.