Granted Patent B2

US 12,298,295 · App. 18/524,841 · Granted May 13, 2025

Inventors: Bradford R. Everman (Haddonfield, NJ); Brian Scott Bradke (Brookfield, VT)

G01N33/497G16H50/30G01N33/4975G08B21/182

Abstract

Claims (48)

1. An apparatus for human performance exhalation sensing, comprising:

a housing, wherein the housing comprises:

an inlet tube configured to receive exhaled gas from an individual;

a sensing device positioned within the inlet tube;

at least a processor; and

a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to:

receive performance data related to at least a task assigned to the individual;

generate a performance metric of the individual as a function of the performance data, wherein the performance metric comprises a performance parameter associated with the at least a task;

generate a breath profile of the individual as a function of data collected from the exhaled gas;

generate a performance determination of the individual as a function of the performance parameters and the breath profile by generating a performance determination machine learning model which comprises:

receiving training data, wherein the training data correlates a plurality of breath parameter data and a plurality of performance data to a plurality of performance determination data;

training, iteratively, the performance determination machine learning model using the training data, wherein training the performance determination machine learning model includes retraining the performance determination machine learning model with feedback from previous iterations of the performance determination machine learning model;

generating the performance determination using the trained performance determination machine learning model; and

alert the individual based on the generated performance determination.

2. The apparatus of claim 1 , wherein the performance parameter comprises a parameter related to a biological performance of the individual.

3. The apparatus of claim 1 , wherein the performance parameter comprises a physiological parameter.

4. The apparatus of claim 1 , wherein generating the performance metric comprises:

classifying the performance data into the performance parameter using a performance parameter classifier, wherein classifying the performance data to the performance parameter comprises:

classifying the at least a task into at least a task category associated with the performance parameter.

5. The apparatus of claim 1 , wherein the breath profiles comprises a plurality of breath parameters.

6. The apparatus of claim 1 , wherein generating the performance determination comprises tuning the performance determination as a function of the breath profile.

7. The apparatus of claim 1 , wherein the performance determination comprises a performance score.

8. The apparatus of claim 1 , wherein generating the performance determination comprises:

determining a confidence metric associated with the performance determination using the performance determination machine learning model.

9. The apparatus of claim 1 , wherein the memory further contains instructions configuring the at least a processor to:

display the alert using a display device on an exterior surface of the housing to alert the individual.

10. A method of using a human performance exhalation sensor, comprising:

providing an inlet tube to a user, wherein the inlet tube is configured to receive exhaled gas from an individual;

receiving, by at least a processor communicatively connected to the sensing device, performance data related to at least a task assigned to the individual;

generating a performance metric of the individual as a function of the performance data, wherein the performance metric comprises a performance parameter associated with the at least a task;

generating, by the at least a processor, a breath profile of the individual as a function of data collected from the exhaled gas;

generating, by the at least a processor, a performance determination as a function of the performance parameter and the breath profile by generating a performance determination machine learning model which comprises:

receiving training data, wherein the training data correlates a plurality of breath parameter data and a plurality of performance data to a plurality of performance determination data;

training, iteratively, the performance determination machine learning model using the training data, wherein training the performance determination machine learning model includes retraining the performance determination machine learning model with feedback from previous iterations of the performance determination machine learning model;

generating the performance determination using the trained performance determination machine learning model; and

alerting, by the at least a processor, the individual based on the generated performance determination.

11. The method of claim 10 , wherein the performance parameter comprises a parameter related to a biological performance of the individual.

12. The method of claim 10 , wherein the performance parameter comprises a physiological parameter.

13. The method of claim 10 , wherein generating the performance metric comprises:

classifying the performance data into the performance parameter using a performance parameter classifier, wherein classifying the performance data to the performance parameter comprises:

classifying the at least a task into at least a task category associated with the performance parameter.

14. The method of claim 10 , wherein the breath profiles comprises a plurality of breath parameters.

15. The apparatus of claim 1 , wherein generating the performance determination comprises tuning the performance determination as a function of the breath profile.

16. The method of claim 10 , wherein the performance determination comprises a performance score.

17. The method of claim 10 , wherein generating the performance determination comprises:

determining a confidence metric associated with the performance determination using the performance determination machine learning model.

18. The method of claim 10 , wherein the memory further contains instructions configuring the at least a processor to:

display the alert using a display device on an exterior surface of the housing to alert the individual.

Continuity (2)

References Cited (17)