Systems and Methods for Assessment of Fatigue-Related Contextual Performance Using Historical Incident Data

• US 20120089553A1
• Filed: 09/19/2011
• Published: 04/12/2012
• Est. Priority Date: 09/20/2010
• Status: Active Grant

• Current Assignee: Pulsar Informatics, Inc.
• Original Assignee: Pulsar Informatics, Inc.
• Inventors: Mollicone, Daniel Joseph, Mott, Christopher Grey
• Granted Patent: US 8,812,428 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Disclosed herein are methods for transforming numerical output of mathematical-fatigue models into contextual performance metrics, including without limitation, performance, incident and/or accident-related metrics associated with particular activities and/or with particular environments, such as but not limited to: the number and severity of injuries or cost of repairs associated with a particular incident, increases in insurance premiums, a performance rate, an error rate and/or the like.

Claims

1. A method for assessing the impact of fatigue on performance, the method comprising:

determining an initial model-predicted fatigue level of an individual at an initial time;

transforming the initial model-predicted fatigue level into an initial contextual performance metric by applying a mapping function to the initial model-predicted fatigue level, the mapping function based at least in part on information contained in an historical fatigue database.

2. A method according to claim 1 comprising:

determining an additional model-predicted fatigue level of the individual at an additional time, the additional time after the initial time and during a time interval of interest;

transforming the additional model-predicted fatigue levels into an additional contextual performance metric by applying the mapping function to the additional model-predicted fatigue level.

3. A method according to claim 1 wherein determining the initial model-predicted fatigue level comprises applying a fatigue-measurement technique to obtain a current fatigue level of the individual at a current time.

4. A method according to claim 3 wherein determining the initial model-predicted fatigue level comprises applying a fatigue-modeling technique to predict the initial model-predicted fatigue level and wherein applying the fatigue-modeling technique is based at least in part on the current fatigue level.

5. A method according to claim 1 wherein determining the initial model-predicted fatigue level comprises applying a fatigue-modeling technique to estimate the initial model-predicted fatigue level.

6. A method according to claim 2 comprising receiving schedule data for the individual in the time interval of interest, the schedule data comprising at least one of:

activity schedule data relating to times during the time interval of interest that the individual is expected to be performing a particular activity; and

sleep schedule data relating to times during the time interval of interest that the individual is expected to be sleeping.

7. A method according to claim 6 wherein determining the additional model-predicted fatigue level comprises applying a fatigue-modeling technique to estimate the additional model-predicted fatigue level.

8. A method according to claim 7 wherein applying the fatigue-modeling technique is based at least in part on the schedule data.

9. A method according to claim 8 wherein the time interval of interest takes place in the future and the schedule data comprises sleep schedule data which assumes that the individual will be awake during the time interval of interest.

10. A method according to claim 2 comprising:

receiving a plurality of hypothetical schedule data scenarios, each hypothetical schedule data scenario comprising at least one of;

hypothetical activity schedule data relating to times during the time interval of interest that the individual is expected to be performing a particular activity; and

hypothetical sleep schedule data relating to times during the time interval of interest that the individual is expected to be sleeping;

for each hypothetical schedule data scenario, repeating the steps of;

determining the additional model-predicted fatigue level; and

transforming the additional model-predicted fatigue levels into the additional contextual performance metric;

to thereby obtain, for each hypothetical schedule data scenario, a scenario-specific additional contextual performance metric; and

comparing the scenario-specific additional contextual performance metrics to one another.

11. A method according to claim 10 wherein, for each hypothetical schedule data scenario, determining the additional model-predicted fatigue level comprises applying a fatigue-modeling technique to estimate the additional model-predicted fatigue level and wherein applying the fatigue-modeling technique is based at least in part on the hypothetical schedule data scenario.

12. A method according to claim 2 wherein the contextual performance metric comprises one or more of:

an incident-related metric associated with a particular activity; and

an incident-related metric associated with a particular environment.

13. A method according to claim 2 wherein the contextual performance metric comprises one or more of:

a performance metric associated with a particular activity; and

a performance metric associated with a particular environment.

14. A method according to claim 2 wherein the historical fatigue database is populated by records, each record comprising:

a contextual performance metric field comprising a contextual performance metric value obtained from one or more historical events;

a fatigue level field comprising a fatigue level value obtained from one or more individuals associated with the one or more historical events; and

one or more classifier fields comprising record-classification criteria associated with the one or more historical events.

15. A method according to claim 14 wherein obtaining the contextual performance metric value from the one or more historical events comprises at least one of:

measuring the contextual performance metric value; and

sensing the contextual performance metric value.

16. A method according to claim 14 wherein obtaining the fatigue level value from the one or more individuals associated with the one or more historical events comprises at least one of:

applying a fatigue-measurement technique to the one or more individuals; and

applying a fatigue-modeling technique to the one or more individuals.

17. A method according to claim 14 wherein the record-classification criteria of at least one of the one or more classifier fields comprises an environment type of the one or more historical events.

18. A method according to claim 17 wherein the record-classification criteria of at least one of the one or more classifier fields comprises an activity type of the one or more historical events.

19. A method according to claim 14 wherein the record-classification criteria of at least one of the one or more classifier fields comprises an activity type of the one or more historical events.

20. A method according to claim 14 wherein one or more records populating the historical fatigue database may be created by one or more of:

a manual user entry through an electronic interface, automatic entry through a networked communication interface, and extraction of entries from another database or information system.

21. A method according to claim 2 wherein transforming the additional model-predicted fatigue levels into the additional contextual performance metric comprises obtaining the mapping function by selecting the mapping function from among a plurality of existing mapping functions previously created based on information contained in the historical fatigue database.

22. A method according to claim 21 wherein the plurality of existing mapping functions is stored in a mapping function database.

23. A method according to claim 2 wherein transforming the additional model-predicted fatigue levels into the additional contextual performance metric comprises obtaining the mapping function by creating the mapping function based on information contained in the historical fatigue database.

24. A method according to claim 14 wherein transforming the additional model-predicted fatigue levels into the additional contextual performance metric comprises obtaining the mapping function by creating the mapping function based on information contained in the historical fatigue database.

25. A method according to claim 24 wherein creating the mapping function comprises:

selecting a subset of the historical fatigue database based at least in part on record-classification criteria in the one or more classifier fields associated with each record; and

creating the mapping function using the contextual performance metric values and fatigue level values of the records in the database subset.

26. A method according to claim 24 wherein creating the mapping function using the contextual performance metric values and fatigue level values of the records in the database subset comprises using a curve fitting technique to determine the mapping function to be a mathematical function which optimally relates the fatigue level values of the database subset to corresponding performance level values of the database subset.

27. A method according to claim 26 wherein applying the mapping function to the additional model-predicted fatigue level comprises outputting, as the additional contextual performance metric, a result of the mathematical function computed on a basis of the additional model-predicted fatigue-level.

28. A method according to claim 25 wherein the mapping function is a discrete mapping function and wherein creating the mapping function using the contextual performance metric values and fatigue level values of the records in the database subset comprises:

grouping the records into a plurality of zones, each zone spanning a range of possible fatigue levels; and

for each zone, combining the contextual performance metric values of the records grouped into the zone to determine a zone-based contextual performance metric value; and

determining the mapping function to be one of the zone-based contextual performance metric values which depends on the zone into which the additional model-predicted level belongs.

29. A method according to claim 28 wherein grouping the records into a plurality of zones comprises assigning each zone an at least approximately equal range of possible fatigue levels.

30. A method according to claim 28 wherein grouping the records into a plurality of zones comprises selecting zone boundaries so as to obtain desired zone-based contextual performance metric values for each zone.

31. A method according to claim 28 wherein combining the contextual performance metric values of the records grouped into the zone to determine the zone-based contextual performance metric value comprises averaging the contextual performance metric values of the records grouped into the zone.

32. A method according to claim 28 wherein applying the mapping function to the additional model-predicted fatigue level comprises determining the zone into which the additional model-predicted fatigue-level belongs and outputting, as the additional contextual performance metric, the corresponding zone-based contextual performance metric value.

33. A method for assessing the impact of fatigue on performance, the method comprising:

determining an initial model-predicted fatigue level of an individual at an initial time;

receiving schedule data for the individual in a future time interval of interest, the schedule data comprising at least one of;

activity schedule data relating to times during the future time interval of interest that the individual is expected to be performing a particular activity; and

sleep schedule data relating to times during the future time interval of interest that the individual is expected to be sleeping;

determining a future model-predicted fatigue level of the individual at a future time, the future time after the initial time and during the future time interval of interest;

transforming the initial and future model-predicted fatigue levels into initial and future contextual performance metrics by applying a mapping function to the initial and future model-predicted fatigue levels, the mapping function based at least in part on information contained in an historical fatigue database;

wherein determining the future model-predicted fatigue level is based at least in part on the schedule data; and

wherein the historical fatigue database is populated by records, each record comprising;

a contextual performance metric field comprising a contextual performance metric value obtained from one or more historical events;

a fatigue level field comprising a fatigue level value obtained from one or more individuals associated with the one or more historical events; and

one or more classifier fields comprising record-classification criteria associated with the one or more historical events.

34. A computer program product embodied in a non-transitory medium and comprising computer-readable instructions which when executed by a suitable comprises cause the computer to perform a method for assessing the impact of fatigue on performance, the method comprising:

determining an initial model-predicted fatigue level of an individual at an initial time;

transforming the initial model-predicted fatigue level into an initial contextual performance metric by applying a mapping function to the initial model-predicted fatigue level, the mapping function based at least in part on information contained in an historical fatigue database.

35. A computer program product according to claim 34 wherein the method comprises:

determining an additional model-predicted fatigue level of the individual at an additional time, the additional time after the initial time and during a time interval of interest;

transforming the additional model-predicted fatigue levels into an additional contextual performance metric by applying the mapping function to the additional model-predicted fatigue level.