Identifying true positive data within a set of blast exposure data

Patent metadata

Field	Value
Publication number	US-12169149-B2
Application number	US-202318317669-A
Country	US
Kind code	B2
Filing date	May 15, 2023
Priority date	Nov 9, 2020
Publication date	Dec 17, 2024
Grant date	Dec 17, 2024

Abstract

Methods, systems, and computer-readable media for identifying true positive data within a set of blast exposure data. An equation fit is applied to generate one or more equations corresponding to portions of pressure data within the set of blast exposure data. The one or more equations are compared to the pressure data to determine if respective portions of the blast exposure data relates to true positive data.

First claim

Having thus described various embodiments of the invention, what is claimed as new and desired to be protected by Letters Patent includes the following:

1. A method of identifying true positives from a set of blast exposure data using at least one processor of a user device, the method comprising:
receiving, at the user device, the set of blast exposure data comprising pressure data over time including at least one pressure trace received from one or more blast sensors configured to detect blast pressure associated with a blast exposure;
applying a filter to the pressure data to thereby remove noise from the pressure data;
applying an equation fit to one or more portions of the pressure data to generate one or more respective equations;
comparing one or more equation parameters from the one or more respective equations to one or more parameters from the pressure data; and
determining whether the one or more portions of the pressure data correspond to true positive data associated with the blast exposure based on comparing of the one or more equation parameters to the one or more parameters from the pressure data.

2. The method of claim 1 , further comprising:
selecting the one or more portions of the pressure data that correspond to the true positive data; and
removing a remaining portion of the pressure data that does not correspond to the true positive data.

3. The method of claim 1 , further comprising:
prior to applying the equation fit to the one or more portions of the pressure data, applying a false positive filter to the set of blast exposure data to remove one or more identified portions of the pressure data that correspond to false positive data.

4. The method of claim 1 , wherein the equation fit comprises a Friedlander equation fit.

5. The method of claim 1 , further comprising:
calculating time derivative data based on the pressure data.

6. The method of claim 5 , further comprising:
detecting a plurality of slopes within the time derivative data;
removing one or more slopes from the plurality of slopes responsive to determining that the one or more slopes are within a predetermined threshold from a standard deviation of the time derivative data.

7. The method of claim 6 , further comprising:
merging two or more remaining slopes of the plurality of slopes within the time derivative data.

8. One or more non-transitory computer-readable media that store computer-executable instructions that, when executed by at least one processor of a user device, perform a method of identifying true positives from a set of blast exposure data, the method comprising:
receiving, at the user device, the set of blast exposure data comprising pressure data over time including at least one pressure trace received from one or more blast sensors configured to detect blast pressure associated with a blast exposure;
applying an equation fit to one or more portions of the pressure data to generate one or more respective equations;
comparing one or more equation parameters from the one or more respective equations to one or more parameters from the pressure data; and
determining whether the one or more portions of the pressure data correspond to true positive data associated with the blast exposure based on comparing of the one or more equation parameters to the one or more parameters from the pressure data.

9. The one or more non-transitory computer-readable media of claim 8 , wherein the method further comprises:
applying a low-pass filter to the pressure data to thereby remove noise from the pressure data.

10. The one or more non-transitory computer-readable media of claim 8 , wherein the method further comprises:
determining that a portion of the set of blast exposure data is between a predetermined negative threshold and a predetermined positive threshold; and
responsive to determining that the portion of the set of blast exposure data is between the predetermined negative threshold and the predetermined positive threshold, removing the portion of the set of blast exposure data.

11. The one or more non-transitory computer-readable media of claim 8 , wherein the method further comprises:
comparing one or more impulses from the one or more respective equations to one or more original impulses from the set of blast exposure data.

12. The one or more non-transitory computer-readable media of claim 11 , wherein the one or more impulses comprise a zero crossing impulse from the one or more respective equations.

13. The one or more non-transitory computer-readable media of claim 8 , wherein the method further comprises:
determining that one or more subsequent portions of the pressure data do not correspond to the true positive data based on a comparison of the one or more equation parameters corresponding to the one or more subsequent portions of the pressure data to the one or more parameters from the pressure data; and
removing the one or more subsequent portions of the pressure data from the set of blast exposure data.

14. A method of identifying true positives from a set of blast exposure data using at least one processor of a user device, the method comprising:
receiving, at the user device, the set of blast exposure data comprising pressure data over time including at least one pressure trace received from one or more blast sensors configured to detect blast pressure associated with a blast exposure;
identifying one or more features within the pressure data,
wherein the one or more features are associated with one or more predefined false positive classes;
determining a false positive score associated with the set of blast exposure data based on the one or more features;
removing at least a portion of the set of blast exposure data based on the false positive score;
applying an equation fit to one or more portions of the pressure data to generate one or more respective equations;
comparing one or more equation parameters from the one or more respective equations to one or more parameters from the pressure data; and
determining whether the one or more portions of the pressure data correspond to true positive data associated with the blast exposure based on comparing of the one or more equation parameters to the one or more parameters from the pressure data.

15. The method of claim 14 , further comprising:
applying a low-pass filter to the pressure data to thereby remove noise from the pressure data.

16. The method of claim 14 , wherein the one or more predefined false positive classes comprises a negative impulse class associated with a negative impulse at a beginning portion of a waveform within the set of blast exposure data.

17. The method of claim 14 , further comprising:
integrating the set of blast exposure data over time to produce impulse data; and
integrating the one or more respective equations over time to produce fit impulse data.

18. The method of claim 17 , further comprising:
comparing one or more impulses from the fit impulse data to one or more original impulses from the impulse data.

19. The method of claim 18 , wherein the one or more impulses comprise a zero crossing impulse from the one or more respective equations.

20. The method of claim 14 , further comprising:
determining a mean squared error between the one or more respective equations and one or more corresponding portions of the set of blast exposure data.

Assignees

• Applied Res Associates Inc

Inventors

• Wiri Suthee
• Ortley David J

Classifications

• A42B3/046

  Means for detecting hazards or accidents · CPC title

• G06F18/2113

  by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/9035

  Filtering based on additional data, e.g. user or group profiles · CPC title

• G06F2218/00

  Aspects of pattern recognition specially adapted for signal processing · CPC title