Method and system for discerning a false positive in a fall detection signal

• US 9,638,711 B2
• Filed: 06/18/2012
• Issued: 05/02/2017
• Est. Priority Date: 06/17/2011
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Telematics Inc. (Verizon Communications Inc.)
• Inventors: Barfield, James R., Taylor, Thomas S., Kalinadhabhotla, Deep
• Primary Examiner(s): Rivera Vargas, Manuel
• Application Number:
  US13/526,421
• Publication Number:
  US 20130197856A1
• Time in Patent Office: 1,779 Days
• Field of Search: 702141
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G01P 15/0891 with indication of predetermined acceleration values G01P15/135 takes precedence
• CPC Class Codes: G01P 15/18 in two or more dimensions

Abstract

Methods reduce the likelihood of an MPERS device falsely reporting a high acceleration event as a fall impact. The device stores acceleration data acquired before the high acceleration and afterward. If a number of samples of magnitude values from accelerometer sensors in the device acquired during as interval before the high acceleration that approach 0G exceeds a predetermined number, the high acceleration is deemed from a non-fall. Acceleration sensors can also indicate an orientation change before/after the high acceleration, and a barometric pressure sensor can do the same, to further characterize an event as a non-fall. A method compares current event data to composite data sets that have been determined from a plurality of empirically derived data sets of fall and non-fall events. High correlations can indicate falls, or non-falls, respectively. Further statistical analysis of data acquired after an event reduces the likelihood of falsely indicating a fall.

Claims

1. A method, comprising:

receiving, by a server and from a mobile device, a plurality of accelerometer values generated by the mobile device;

determining, by the server and based on the plurality of accelerometer values, a plurality of acceleration magnitude values;

determining, by the server, that at least one of the plurality of acceleration magnitude values satisfies an acceleration magnitude threshold;

identifying, by the server, a potential fall event at a time period based on the at least one of the plurality of acceleration magnitude values satisfying the acceleration magnitude threshold,

the plurality of acceleration magnitude values including a set of acceleration magnitude values corresponding to a set of time periods prior to the time period;

determining, by the server and based on identifying the potential fall event, a quantity of the set of acceleration magnitude values that are below a free fall magnitude threshold;

determining, by the server, a total free fall interval based on the quantity of the set of acceleration magnitude values that are below the free fall magnitude threshold;

determining, by the server, that the total free fall interval satisfies a free fall interval threshold;

determining, by the server and based on the total free fall interval satisfying the free fall interval threshold, that a non-fall event occurred; and

transmitting, by the server and to a service provider device, an indication that the non-fall event occurred to indicate that the potential fall event is a false positive.

2. The method of claim 1, further comprising:

storing acceleration data generated from an accelerometer device of the mobile device during an event signature window,

where the event signature window is an amount of time before an acceleration magnitude signal from the accelerometer device meets a criterion;

storing the acceleration data as a fall event data set in a fall event data set library if the acceleration data resulted from a fall event; and

storing the acceleration data as a non-fall event data set in a non-fall event data set library if the acceleration data resulted from a non-fall event.

3. The method of claim 2, further comprising:

determining maximum acceleration magnitude values from a plurality of fall event data sets in the fall event data set library; and

identifying a minimum of the maximum acceleration magnitude values as the acceleration magnitude threshold.

4. The method of claim 3, further comprising:

determining, for the plurality of fall event data sets in the fall event data set library, free fall intervals that precede respective maximum acceleration magnitude values;

identifying, for the plurality of fall event data sets in the fall event data set library, minimum acceleration magnitude values during the free fall intervals; and

determining, from the plurality of fall event data sets in the fall event data set library, a maximum of the minimum acceleration magnitude values during the respective free fall intervals as the free fall magnitude threshold.

5. The method of claim 1, further comprising:

determining, based on the non-fall event occurring, a plurality of acceleration component values from the set of acceleration magnitude values,

the plurality of acceleration component values corresponding to an acceleration component along one of a plurality of perpendicular axes of the set of acceleration magnitude values;

determining, for the plurality of acceleration component values, a number of zero-axis crossing events; and

determining that the non-fall event occurred if the number of zero-axis crossing events is greater than one.

6. The method of claim 5, further comprising:

integrating acceleration magnitude values, of the plurality of acceleration magnitude values, corresponding to each of the plurality of acceleration component values between two zero-axis crossing events;

scaling, based on integrating the acceleration magnitude values, the acceleration component values between the two zero-axis crossing events to adjust the acceleration component values to values comparable to a fall event or to a non-fall event without spin;

computing, based on scaling the acceleration component values, scaled acceleration magnitudes; and

using the scaled acceleration magnitudes as the acceleration magnitude values.

7. The method of claim 1, further comprising:

determining a plurality of other free fall intervals; and

identifying a longest free fall interval of the plurality of other free fall intervals,

where the free fall interval threshold is the longest free fall interval.

8. The method of claim 1, further comprising:

performing, based on the non-fall event occurring, a correlation function based on a plurality of composite non-fall event data sets to produce a plurality of correlation coefficients; and

determining, based on performing the correlation function, that the non-fall event occurred if the plurality of correlation coefficients satisfies a respective threshold corresponding to the plurality of composite non-fall event data sets.

9. The method of claim 1, further comprising:

performing, based on the non-fall event occurring, a correlation function based on a plurality of composite fall event data sets to produce a plurality of correlation coefficients; and

determining, based on performing the correlation function, that the non-fall event occurred if one of the plurality of correlation coefficients is less than a respective threshold corresponding to the plurality of composite fall event data sets.

10. A device, comprising:

one or more processors to;

receive a plurality of accelerometer values generated by a mobile device;

determine, based on receiving the plurality of accelerometer values, a plurality of acceleration magnitude values;

determine that at least one of the plurality of acceleration magnitude values satisfies an acceleration magnitude threshold;

identify a potential fall event at a time period based on the at least one of the plurality of acceleration magnitude values satisfying the acceleration magnitude threshold,

the plurality of acceleration magnitude values including a set of acceleration magnitude values corresponding to a set of time periods prior to the time period;

determine, based on identifying the potential fall event, a quantity of the set of acceleration magnitude values that are below a free fall magnitude threshold;

determine a total free fall interval based on the quantity of the set of acceleration magnitude values that are below the free fall magnitude threshold;

determine that the total free fall interval satisfies a free fall interval threshold;

determine, based on the total free fall interval satisfying the free fall interval threshold, that a non-fall event occurred; and

transmit, to a service provider device, a signal that the non-fall event occurred to indicate that the potential fall event is a false positive.

11. The device of claim 10, where the one or more processors are further to:

determine, based on the non-fall event occurring, a plurality of acceleration component values from the set of acceleration magnitude values,

the plurality of acceleration component values corresponding to an acceleration component along one of a plurality of perpendicular axes of the set of acceleration magnitude values;

determine, for the plurality of acceleration component values, a number of zero-axis crossing events; and

determine that the non-fall event occurred if the number of zero-axis crossing events is greater than one.

12. The device of claim 11, where the one or more processors are further to:

integrate acceleration magnitude values, of the plurality of acceleration magnitude values, corresponding to each of the plurality of acceleration component values that occur between two zero-axis crossing events;

scale, based on integrating the acceleration magnitude values, the acceleration component values between the two zero-axis crossing events to adjust the acceleration component values to values comparable to a fall event or to a non-fall event without spin;

compute, based on scaling the acceleration component values, scaled acceleration magnitudes; and

use the scaled acceleration magnitudes as the acceleration magnitude values.

13. The device of claim 10, where the one or more processors are further to:

determine a plurality of other free fall intervals; and

identify a longest free fall interval of the plurality of other free fall intervals, where the free fall interval threshold is the longest free fall interval.

14. The device of claim 10, where the one or more processors are further to:

perform, based on the non-fall event occurring, a correlation function based on a plurality of composite non-fall event data sets to produce a plurality of correlation coefficients; and

determine, based on performing the correlation function, that the non-fall event occurred if the plurality of correlation coefficients satisfies a respective threshold corresponding to the plurality of composite non-fall event data sets.

15. The device of claim 10, where the one or more processors are further to:

perform, based on the non-fall event occurring, a correlation function based on a plurality of composite fall event data sets to produce a plurality of correlation coefficients; and

determine, based on performing the correlation function, that the non-fall event occurred if one of the plurality of correlation coefficients is less than a respective threshold corresponding to the plurality of composite fall event data sets.

16. A method, comprising:

receiving, by a server, acceleration data from an accelerometer device,

the acceleration data comprising a plurality of accelerometer values;

storing, by the server, the acceleration data corresponding to an event signature window,

the event signature window being an amount of time before a potential fall event;

determining, by the server and based on the plurality of accelerometer values, a plurality of acceleration magnitude values;

determining, by the server, that at least one of the plurality of acceleration magnitude values satisfies an acceleration magnitude threshold;

identifying, by the server, flail the potential fall event at a time period based on the at least one of the plurality of acceleration magnitude values satisfying the acceleration magnitude threshold,

the plurality of acceleration magnitude values including a set of acceleration magnitude values corresponding to a set of time periods prior to the time period, and

the set of time periods prior to the time period corresponding to the event signature window;

determining, by the server and based on identifying the potential fall event, a quantity of the set of acceleration magnitude values that are below a free fall magnitude threshold;

determining, by the server, a total free fall interval based on the quantity of the set of acceleration magnitude values that are below the free fall magnitude threshold;

storing, by the server, the acceleration data as a fall event data set in a fall event data set library if the total free fall interval is less than a free fall interval threshold; and

storing, by the server, the acceleration data as a non-fall event data set in a non-fall event data set library if the total free fall interval satisfies the free fall interval threshold,

the potential fall event being a false positive if the total free fall interval satisfies the free fall interval threshold.

17. The method of claim 16, further comprising:

determining maximum acceleration magnitude values from a plurality of fall event data sets in the fall event data set library; and

identifying a minimum of the maximum acceleration magnitude values as the acceleration magnitude threshold.

18. The method of claim 17, further comprising:

determining, for the plurality of fall event data sets in the fall event data set library, free fall intervals that precede respective maximum acceleration magnitude values;

identifying, for the plurality of fall event data set in the fall event data set library, minimum acceleration magnitude values during the free fall intervals; and

determining, from the plurality of fall event data sets in the fall event data set library, a maximum of the minimum acceleration magnitude values during the respective free fall intervals as the free fall magnitude threshold.

19. The method of claim 16, further comprising:

determining a plurality of acceleration component values from the set of acceleration magnitude values,

the plurality of acceleration component values corresponding to an acceleration component along one of a plurality of perpendicular axes of the set of acceleration magnitude values;

determining, for the plurality of acceleration component values, a number of zero-axis crossing events; and

determining that the acceleration data corresponds to a non-fall event occurred if the number of zero-axis crossing events is greater than one.

20. The method of claim 19, further comprising:

integrating acceleration magnitude values, of the plurality of acceleration magnitude values, corresponding to each of the plurality of acceleration component values between two zero-axis crossing events;

scaling, based on integrating the acceleration values, the acceleration component values between the two zero-axis crossing events to adjust the plurality of acceleration component values to values comparable to a fall event or to a non-fall event without spin;

computing, based on scaling the acceleration component values, scaled acceleration magnitudes; and

using the scaled acceleration magnitudes as the acceleration magnitude values.