APPARATUS AND METHOD FOR DETERMINING A SEDENTARY STATE OF A SUBJECT

• US 20180125394A1
• Filed: 05/06/2016
• Published: 05/10/2018
• Est. Priority Date: 05/11/2015
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Sartor, Francesco, Schuijers, Erik Gosuinus Petrus, Papini, Gabriele, Ruijs, Louisa Simone, Lemmens, Paul Marcel Carl, van den Broek, Chantal Nathalie
• Granted Patent: US 10,980,446 B2
• Time in Patent Office: 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 5/1118 Determining activity level
• CPC Class Codes: A61B 5/7207 of noise induced by motion artifacts
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• 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 5/74 Details of notification to user or communication with user or patient indicating measured values G01D7/00; user input means input or output arrangements for computers G06F3/00
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The present invention relates to distinguishing different sedentary states of a subject. A sedentary state can refer to standing, sitting and/or lying. An apparatus for determining a sedentary state of a subject is presented that comprises a sensor interface for obtaining a movement signal indicative of a movement of the subject; an extraction unit for extracting a signal feature indicative of postural control oscillations of the subject from the movement signal, wherein the signal feature indicative of postural control oscillations is indicative of center of mass motion oscillations for preventing the subject from falling; and a classifier for classifying a sedentary state of the subject based on the signal feature indicative of postural control oscillations of the subject. Further, a corresponding method, computer program and system are presented.

Claims

1. An apparatus for determining a sedentary state of a subject comprising:

a sensor interface for obtaining a movement signal indicative of a movement of the subject;

characterized by

an extraction unit for extracting a signal feature indicative of postural control oscillations of the subject from the movement signal, wherein the signal feature indicative of postural control oscillations is indicative of center of mass motion oscillations for preventing the subject from falling; and

a classifier for classifying a sedentary state of the subject based on the signal feature indicative of postural control oscillations of the subject.

2. The apparatus according to claim 1, wherein classifying a sedentary state comprises a classification into at least one of standing, sitting and/or lying.

3. The apparatus according to claim 1, wherein the classifier for classifying a sedentary state of the subject is configured for classifying the sedentary state

as a first sedentary state, if the signal feature indicative of postural control oscillations of the subject is larger or equal to a first predetermined threshold, or

as a second sedentary state, if the signal feature indicative of postural control oscillations of the subject is smaller than the first predetermined threshold.

4. The apparatus according to claim 1, wherein said signal feature indicative of postural control oscillations comprises at least one of an oscillation amplitude, an oscillation variance, and a sum of distances of values of the movement signal from a center of a cloud of said values of the movement signal.

5. The apparatus according to claim 1, wherein the extraction unit for extracting a signal feature indicative of postural control oscillations is configured for determining signal windows in the movement signal indicative of voluntary movements;

and to discard the signal windows that are indicative of voluntary movements.

6. The apparatus according to claim 5, wherein the extraction unit for extracting a signal feature indicative of postural control oscillations is configured for determining signal windows in the movement signal indicative of voluntary movements by determining if an amplitude and/or variance of the movement signal exceeds a predetermined voluntary movement threshold and/or by determining if a spectral content of the movement signal corresponds to a voluntary movement spectrum.

7. An apparatus according to claim 1, wherein the extraction unit for extracting a signal feature indicative of postural control oscillations is configured to determine a gravity vector and to determine a signal features indicative of postural control oscillations which are substantially perpendicular to the gravity vector.

8. The apparatus according to claim 1, wherein said extraction unit and/or said classification unit comprises an adaptive threshold for extracting a signal feature indicative of postural control oscillations of the subject from the movement signal or for classifying a sedentary state based on the signal feature indicative of postural control oscillations of the subject respectively.

9. The apparatus according to claim 1, further comprising:

a timing unit for determining an duration of the sedentary state; and

an alert unit for providing an alert signal if the duration of the sedentary state exceeds a predetermined time budget.

10. The apparatus according to claim 9, wherein the predetermined time budget is determined based on at least one of user characteristics, age, gender, pregnancy status, family history, edema, varicose veins problems, and/or occupation.

11. The apparatus according to claim 9, wherein the alert signal is at least one of an audible signal, a visual signal and a tactile signal.

12. A system for determining a sedentary state of a subject comprising:

a movement sensor, in particular an accelerometer, for providing the movement signal; and

the apparatus for determining a sedentary state of a subject according to claim 1.

13. Method for determining a sedentary state of a subject comprising:

obtaining a movement signal indicative of a movement of the subject;

characterized by

extracting a signal feature indicative of postural control oscillations of the subject from the movement signal, wherein the signal feature indicative of postural control oscillations is indicative of center of mass motion oscillations for preventing the subject from falling; and

classifying a sedentary state of the subject based on the signal features indicative of postural control oscillations of the subject.

14. Computer program comprising program code means for causing a computer to carry out the steps of the method as claimed in claim 13 when said computer program is carried out on a computer.