Fall detection
Proposed are concepts for distinguishing between fall events and non-fall-events for different sub-groups within a monitored group (i.e., monitored population) of subjects. It is proposed that an entire/group population of monitored subjects may be portioned into sub-groups, each sub-group consisting of a plurality of members (i.e., subjects) having a certain property value or characteristic unique to that group. A respective decision value may be determine for each sub-group, wherein the decision value for a sub-group takes account of a previously obtained false fall detection rate for that sub-group.
1. A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations comprising:
obtaining a first false fall detection rate from a first sub-group of a plurality of sub-groups, the first sub-group comprising one or more subjects each having a characteristic unique to the first sub-group;
obtaining a second false fall detection rate from the first sub-group of the plurality of sub-groups, the second false fall detection rate corresponding to one of:
a previous false fall detection rate; or
an estimated false fall detection rate;
determining that a difference between the first false fall detection rate and the second false fall detection rate satisfies a change threshold;
based on determining that the difference between the first false fall detection rate and the second false fall detection rate satisfies the change threshold, determining, based on the first false fall detection rate, a first value of the sub-group at which the first false fall detection rate satisfies a predetermined rate; and
updating a first fall detection threshold value of the first sub-group with the first value, the updated first fall detection threshold value distinguishing between a fall event and a non-fall-event for each subject of the one or more subjects of the first sub-group.
2. The computer-implemented method of claim 1 , wherein the operations further comprise:
obtaining a third false fall detection rate from a second sub-group of the plurality of sub-groups, the second sub-group comprising one or more subjects each having a characteristic unique to the second sub-group that is different than the characteristic unique to the first sub-group;
determining, based on the third false fall detection rate, a second value of the second sub-group at which the third false fall detection rate satisfies the predetermined rate; and
updating a second fall detection threshold value of the second sub-group with the second value, the updated second fall detection threshold value distinguishing between a fall event and a non-fall-event for each subject of the one or more subjects of the second sub-group.
3. The computer-implemented method of claim 1 , wherein the first false fall detection rate for the first sub-group of the plurality of sub-groups is based on a ratio between a number of false fall detections for the first sub-group and a number of the one or more subjects in the first sub-group.
4. The computer-implemented method of claim 1 , wherein obtaining the first false fall detection rate from the first sub-group of the plurality of sub-groups comprises obtaining, for each respective subject of the one more subjects of the first sub-group, movement data from a wearable device associated with the respective subject.
5. The computer-implemented method of claim 4 , wherein the wearable device comprises a smartwatch.
6. The computer-implemented method of claim 4 , wherein the wearable device comprises a pocket-carried device.
7. The computer-implemented method of claim 4 , wherein the wearable device comprises one or more sensors comprising at least one of:
an accelerometer;
a barometric sensor;
a tilt switch;
a vibration sensor; or
a gyroscope.
8. The computer-implemented method of claim 1 , wherein the predetermined rate is defined to maintain a predetermined minimum detection probability value.
9. The computer-implemented method of claim 1 , wherein the operations further comprise:
identifying the one or more subjects each having the characteristic unique to the first sub-group; and
grouping the one or more subjects into the first sub-group of the plurality of sub-groups.
10. The computer-implemented method of claim 1 , wherein the characteristic unique to the first sub-group comprises at least one of:
a location;
an activity;
an age; or
a medical condition.
11. A system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
obtaining a first false fall detection rate from a first sub-group of a plurality of sub-groups, the first sub-group comprising one or more subjects each having a characteristic unique to the first sub-group;
obtaining a second false fall detection rate from the first sub-group of the plurality of sub-groups, the second false fall detection rate corresponding to one of:
a previous false fall detection rate; or
an estimated false fall detection rate;
determining that a difference between the first false fall detection rate and the second false fall detection rate satisfies a change threshold;
based on determining that the difference between the first false fall detection rate and the second false fall detection rate satisfies the change threshold, determining, based on the first false fall detection rate, a first value of the sub-group at which the first false fall detection rate satisfies a predetermined rate; and
updating a first fall detection threshold value of the first sub-group with the first value, the updated first fall detection threshold value distinguishing between a fall event and a non-fall-event for each subject of the one or more subjects of the first sub-group.
12. The system of claim 11 , wherein the operations further comprise:
obtaining a third false fall detection rate from a second sub-group of the plurality of sub-groups, the second sub-group comprising one or more subjects each having a characteristic unique to the second sub-group that is different than the characteristic unique to the first sub-group;
determining, based on the third false fall detection rate, a second value of the second sub-group at which the third false fall detection rate satisfies the predetermined rate; and
updating a second fall detection threshold value of the second sub-group with the second value, the updated second fall detection threshold value distinguishing between a fall event and a non-fall-event for each subject of the one or more subjects of the second sub-group.
13. The system of claim 11 , wherein the first false fall detection rate for the first sub-group of the plurality of sub-groups is based on a ratio between a number of false fall detections for the first sub-group and a number of the one or more subjects in the first sub-group.
14. The system of claim 11 , wherein obtaining the first false fall detection rate from the first sub-group of the plurality of sub-groups comprises obtaining, for each respective subject of the one more subjects of the first sub-group, movement data from a wearable device associated with the respective subject.
15. The system of claim 14 , wherein the wearable device comprises a smartwatch.
16. The system of claim 14 , wherein the wearable device comprises a pocket-carried device.
17. The system of claim 14 , wherein the wearable device comprises one or more sensors comprising at least one of:
an accelerometer;
a barometric sensor;
a tilt switch;
a vibration sensor; or
a gyroscope.
18. The system of claim 11 , wherein the predetermined rate is defined to maintain a predetermined minimum detection probability value.
19. The system of claim 11 , wherein the operations further comprise:
identifying the one or more subjects each having the characteristic unique to the first sub-group; and
grouping the one or more subjects into the first sub-group of the plurality of sub-groups.
20. The system of claim 11 , wherein the characteristic unique to the first sub-group comprises at least one of:
a location;
an activity;
an age; or
a medical condition.