Detection and compensation method for monitoring the place of activity on the body

• US 10,398,388 B2
• Filed: 03/09/2016
• Issued: 09/03/2019
• Est. Priority Date: 12/15/2005
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Goris, Annelies, Bodlaender, Maarten Peter
• Primary Examiner(s): Dougherty, Sean P
• Application Number:
  US15/064,869
• Publication Number:
  US 20160183883A1
• Time in Patent Office: 1,273 Days
• CPC Class Codes: A61B 2560/0223 of calibration, e.g. protocols for calibrating sensors
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/061 Determining position of a probe within the body employing means separate from the probe, e.g. sensing internal probe position employing impedance electrodes on the surface of the body A61B1/00158 takes precedence
• CPC Class Codes: A61B 5/065 Determining position of the probe employing exclusively positioning means located on or in the probe, e.g. using position sensors arranged on the probe
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor

Abstract

A measuring system (1) comprises a sensor (6) arranged to be attached to a subject for obtaining a measured value representing a physical or a physiological quantity of the subject. The measuring system further comprises means for deriving a subject-related value from the measured value. The sensor is arranged to be attached at one of a plurality of positions on the subject. The measuring system further comprises means for establishing the position of the sensor on the subject. The means for deriving the subject-related value is arranged for deriving the subject-related value also in dependence on the position of the sensor on the subject.

Claims

1. An activity monitor device comprising:

an accelerometer configured to gather a measured signal descriptive of a motion of a subject of the activity monitor device, wherein the accelerometer is positionable to move with any one of a plurality of positions on a body of the subject; and

a processor in communication with the accelerometer and configured to derive subject-related values, wherein the processor is further configured to;

extract at least one feature from the measured signal,

analyze at least one rule based on the at least one feature extracted from the measured signal,

determine a current position of the plurality of positions on the body of the subject at which the accelerometer is positioned based on the analysis of the at least one rule and at least one feature, and

alter the derivation of the subject-related values based on a compensation between the determined current position and a reference position on the body of the subject.

2. The activity monitor of claim 1, wherein the at least one rule is an output of a machine-learning algorithm.

3. The activity monitor of claim 2, wherein the at least one rule includes a neural network.

4. The activity monitor of claim 1, wherein the analysis of the at least one rule comprises performing pattern recognition against the measured signal in at least one of a frequency domain, a time domain, and a time-frequency domain.

5. The activity monitor of claim 1, wherein:

in deriving subject-related values, the processor is configured to operate according to one of multiple modes for processing measured signals; and

in altering the derivation of subject-related values, the processor is configured to change a current mode of the multiple modes in which the processor currently operates.

6. The activity monitor of claim 5, wherein:

a first mode of the multiple modes is associated with a first algorithm for processing the measured signal by the processor to derive the subject-related value; and

a second mode of the multiple modes is associated with a second algorithm for processing the measured signal by the processor to derive the subject-related value.

7. The activity monitor of claim 6, wherein the first mode is associated with at least one compensation value for mathematically transforming a value of the measured signal.

8. A non-transitory machine-readable medium encoded with instructions for execution by a processor, the non-transitory machine-readable medium comprising:

instructions for extracting at least one feature from a measured signal descriptive of a motion of a subject and gathered by an accelerometer that is positionable to move with any one of a plurality of positions on a body of the subject;

instructions for analyzing at least one rule based on the at least one feature extracted from the measured signal;

instructions for determining a current position of the plurality of positions on the body of the subject at which the accelerometer is positioned based on the analysis of the at least one rule and at least one feature; and

instructions for altering a derivation of subject-related values based on a compensation between the determined current position and a reference position on the body of the subject.

9. The non-transitory machine-readable medium of claim 8, wherein the at least one rule is an output of a machine-learning algorithm.

10. The non-transitory machine-readable medium of claim 9, wherein the at least one rule includes a neural network.

11. The non-transitory machine-readable medium of claim 9, wherein the instructions for analyzing the at least one rule comprise instructions performing pattern recognition against the measured signal in at least one of a frequency domain, a time domain, and a time-frequency domain.

12. The non-transitory machine-readable medium of claim 9, wherein:

the instructions for altering the derivation of subject-related values comprise instructions for changing a current mode of deriving subject-related values to one of multiple modes.

13. The non-transitory machine-readable medium of claim 12, wherein:

a first mode of the multiple modes is associated with a first algorithm for processing the measured signal to derive the subject-related value; and

a second mode of the multiple modes is associated with a second algorithm for processing the measured signal to derive the subject-related value.

14. The non-transitory machine-readable medium of claim 12, wherein the first mode is associated with at least one compensation value for mathematically transforming a value of the measured signal.

15. A method for execution by a processor for adapting an activity monitor to a placement on a body of a subject, the method comprising:

extracting at least one feature from a measured signal descriptive of a motion of the subject and gathered by an accelerometer that is positionable to move with any one of a plurality of positions on the body of the subject;

analyzing at least one rule based on the at least one feature extracted from the measured signal;

determining a current position of the plurality of positions on the body of the subject at which the accelerometer is positioned based on the analysis of the at least one rule and at least one feature; and

altering a derivation of subject-related values based on a compensation between the determined current position and a reference position on the body of the subject.

16. The method of claim 15, wherein the at least one rule is an output of a machine-learning algorithm.

17. The method of claim 15, wherein analyzing the at least one rule comprises performing pattern recognition against the measured signal in at least one of a frequency domain, a time domain, and a time-frequency domain.

18. The method of claim 15, wherein altering the derivation of subject-related values comprises changing a current mode of deriving subject-related values to one of multiple modes.

19. The method of claim 18, wherein:

a first mode of the multiple modes is associated with a first algorithm for processing the measured signal to derive the subject-related value; and

a second mode of the multiple modes is associated with a second algorithm for processing the measured signal to derive the subject-related value.

20. The method of claim 18, wherein the first mode is associated with at least one compensation value for mathematically transforming a value of the measured signal.