Method for detecting falls and a fall detector

• US 9,176,932 B2
• Filed: 05/23/2012
• Issued: 11/03/2015
• Est. Priority Date: 11/25/2009
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Baggen, Constant Paul Marie Jozef, Chen, Ningjiang
• Primary Examiner(s): LE, TOAN M
• Application Number:
  US13/478,403
• Publication Number:
  US 20130138395A1
• Time in Patent Office: 1,259 Days
• Field of Search: 702/181, 702/81, 702/127, 702138-139, 702/141, 702/150, 702/179, 702/182, 702188-189, 703/2, 703/4, 703/17, 706 45- 48, 600/587, 600/592, 600/595, 73 137- 138, 73 175- 177, 73/17.9, 733/84
• US Class Current: 1/1
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: G01C 5/06 by using barometric means
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G08B 21/043 detecting an emergency event, e.g. a fall
• CPC Class Codes: G08B 21/0446 worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
• CPC Class Codes: G08B 25/016 Personal emergency signalling and security systems emergency non-personal manually actuated alarm activators G08B25/12

Abstract

A method for detecting a fall by a user includes a method of detecting a fall by a user. The method includes processing measurements obtained from one or more sensors to extract a respective value for a plurality of features associated with a fall. A respective log likelihood ratio for each of the values is determined. Whether the user has fallen is determined based on the determined log likelihood ratios.

Claims

1. A method of detecting a fall by a user, the method comprising:

with a processor or computer, processing measurements obtained from one or more sensors to extract a respective value for a plurality of features associated with a fall, wherein processing the measurements includes processing measurements obtained from an air pressure sensor to extract values indicating changes in altitude;

with a processor or computer, determining a respective log likelihood ratio for each of said extracted values;

with a processor or computer, determining whether the user has fallen based on the determined log likelihood ratios; and

with a transmitter, in response to determining that the user has fallen, transmitting a signal indicating the user has fallen.

2. The method as claimed in claim 1, wherein the step of determining whether the user has fallen comprises determining whether the user has fallen based on a sum of the log like ratios for each of said extracted values.

3. The method as claimed in claim 2, wherein the step of determining whether the user has fallen comprises determining whether the user has fallen based on a weighted sum of the log likelihood ratios for each of said extracted values.

4. The method as claimed in claim 2, wherein the step of determining whether the miser has fallen comprises comparing the sum of the determined log likelihood ratios to a detection threshold.

5. The method as claimed in claim 4, wherein the step of determining whether the user has fallen comprises determining that the user has fallen in the event that the sum of the determined log likelihood ratios is greater than the threshold, and that the user has not fallen in the event that the sum of the determined log likelihood ratios is less than the threshold.

6. The method as claimed in claim 1, wherein the step of determining the log likelihood ratio comprises using said extracted value to look up the log likelihood ratio in a table.

7. The method as claimed in claim 6, wherein the table comprises log likelihood ratios to which the appropriate weighting has been applied.

8. The method as claimed in claim 1, wherein, in the event that a change in altitude exceeds an altitude change threshold, the step of processing measurements further comprises:

processing measurements obtained from an accelerometer to determine a maximum level of activity during a time window around the time that the change in altitude exceeded the altitude change threshold.

9. The method as claimed in claim 8, wherein, in the event that the maximum level of activity during the time window exceeds a first activity threshold, the step of processing measurements further comprises:

processing the measurements obtained from the accelerometer to determine whether there is a predefined period of time within a search window following the maximum level of activity during which the level of activity is below a second activity threshold.

10. The method as claimed in claim 9, wherein, in the event that there is a predefined period of time within a search window following the maximum level of activity during which the level of activity is below the second activity threshold, the step of processing measurements further comprises:

extracting values for further features associated with a fall;

and wherein the steps of determining a log likelihood ratio and determining whether the user has fallen are only executed if the extracted values for all of the further features do not preclude a fail having taken place.

11. A non-transitory computer program product carrying computer-readable code that, when executed on a suitable computer or processor, is configured to cause the computer or processor to perform the steps in the method defined in claim 1.

12. A fall detector, comprising:

a means for determining altitude changes;

an accelerometer configured to determine activity levels;

a processor that is configured to;

extract altitude change values from the determined altitude changes,

determine an altitude change log likelihood ratio for said altitude change values,

when the altitude change log ratio exceeds an altitude change threshold, extract activity level values from the determined activity levels,

determine an activity level log ratio for the activity level values; and

determine whether the user has fallen based on the determined altitude change and activity level log likelihood ratios.

13. An apparatus for detecting a fall by a user, the apparatus comprising:

an altitude sensor means for determining a change in altitude and outputting an altitude signal, the altitude sensor means being configured to be attached to the user;

a computer or processor programmed to;

receive the altitude signal,

extract altitude values from the altitude signal,

determine log likelihood ratios for the altitude values,

analyze the log likelihood ratios to determine whether the user has fallen; and

a transmitter configured to transmit a fall signal when the user is determined to have fallen.

14. The apparatus as claimed in claim 13, further including:

an activity sensor means for determining an activity level and outputting an activity signal, the activity sensor means being configured to be attached to the user; and

wherein the processor is further programmed to;

receive the activity signal,

extract activity values from the activity signal, and

determine actively log likelihood ratios for the activity values to be analyzed with the altitude log likelihood ratios to determine whether the user has fallen.

15. The apparatus as claimed in claim 14, wherein the activity values are extracted in response to is change in extracted altitude values exceeding an altitude change threshold.

16. The apparatus as claimed in claim 15, further including:

other feature sensor means for determining other features and outputting other feature signals; and

wherein the processor is further configured to extract other feature values and determine that the user has fallen only if the extracted other feature values do not preclude a fall having taken place.

17. The apparatus as claimed in claim 14, wherein the activity sensor means includes an accelerometer.

18. The apparatus as claimed in claim 13, wherein the altitude sensor means includes an air pressure sensor.