System and method for improving data coverage in modeling systems

• US 8,086,640 B2
• Filed: 05/30/2008
• Issued: 12/27/2011
• Est. Priority Date: 05/30/2008
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Grichnik, Anthony James, Seskin, Michael, Mason, James Robert
• Primary Examiner(s): Fleurantin, Jean B
• Application Number:
  US12/155,200
• Publication Number:
  US 20090300052A1
• Time in Patent Office: 1,306 Days
• Field of Search: 707600-831, 700/97, 701/5, 703/2
• US Class Current: 707/796
• CPC Class Codes: G05B 17/02 electric

Abstract

A method for modifying data coverage in a modeling system is disclosed. The method may include obtaining data records relating to a plurality of input variables and one or more output parameters and selecting a plurality of input parameters from the plurality of input variables. The method may further include evaluating a coverage of the data records in a modeling space and modifying the coverage of the data records, if a data coverage condition is detected. The method may also include generating a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the data records.

Claims

1. A method for modifying data coverage in a modeling computer system, comprising:

obtaining data records relating to a plurality of input variables and one or more output parameters;

selecting a plurality of input parameters from the plurality of input variables;

evaluating, by a processor of the modeling computer system, a coverage of the data records in a modeling space by determining a data density of the data records in the modeling space, the evaluating including;

dividing the modeling space into a plurality of hyper-quadrants;

calculating a data density for each hyper-quadrant based on a number of data records in the respective hyper-quadrant;

generating a histogram based on the calculated data densities of each hyper-quadrant; and

determining a statistical difference in a data density distribution between the hyper-quadrants based on the generated histogram;

detecting a data coverage condition based on whether the determined statistical difference exceeds a first threshold; and

when a data coverage condition is detected;

modifying the coverage of the data records; and

generating a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the modified data records.

2. The method of claim 1, wherein the statistical difference is determined as a standard deviation of the data density distribution.

3. The method of claim 1, wherein evaluating the coverage of the data records further includes marking sparse hyper-quadrants with data densities below a second threshold, if the data coverage condition is identified.

4. The method of claim 1, wherein modifying the coverage of the data records further includes receiving additional data records from a user for sparse hyper-quadrants in the modeling space.

5. The method of claim 1, wherein modifying the coverage of the data records further includes removing data records from dense hyper-quadrants in the modeling space.

6. The method of claim 1, wherein modifying the coverage of the data records further includes creating additional data records for sparse hyper-quadrants in the modeling space via a symmetric random scatter process proposing input vectors of interest.

7. The method of claim 6, wherein creating the additional data records further includes:

determining starting ranges of the plurality of input parameters;

creating a centroid data record including midpoint values of the starting ranges of the plurality of input parameters;

randomly creating a plurality of sample data records of the plurality of input parameters within the starting ranges of the input parameters;

creating a plurality of SRS data records of the sample data records as symmetric scatters of the plurality of sample data records with respect to the centroid data record;

creating the additional data records by combining the centroid data record, the sample data records, and the SRS data records; and

removing the additional data records that fall out of the sparse hyper-quadrants.

8. The method of claim 1, further including statistically validating the computational model.

9. The method of claim 1, further including optimizing the computational model by maximizing a zeta statistic of the computational model.

10. A computer-based modeling system, comprising:

a database containing data records related to a plurality of input variables and one or more output parameters; and

a processor configured to;

obtain data records relating to the plurality of input variables and one or more output parameters;

select a plurality of input parameters from the plurality of input variables;

evaluate a coverage of the data records in a modeling space by determining a data density of the data records in the modeling space, including;

dividing the modeling space into a plurality of hyper-quadrants; and

calculating the data density for each hyper-quadrant based on a number of data records in the respective hyper-quadrant;

detecting a data coverage condition based on the determined data density of the data records in the modeling space; and

when a data coverage condition is detected;

modify the coverage of the data records; and

generate a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the modified data records.

11. The computer-based modeling system of claim 10, wherein to evaluate the coverage of the data records, the processor is further configured to:

generate a histogram based on the calculated data densities of each hyper-quadrant;

determine a statistical difference in a data density distribution between the hyper-quadrants based on the generated histogram; and

detect the data coverage condition when the statistical difference exceeds a first threshold.

12. The computer-based modeling system of claim 11, wherein the statistical difference is determined as a standard deviation of the data density distribution.

13. The computer-based modeling system of claim 11, wherein to evaluate the coverage of the data records, the processor is further configured to mark sparse hyper-quadrants with data densities below a second threshold, if the data coverage condition is detected.

14. The computer-based modeling system of claim 10, wherein to modify the coverage of the data records, the processor is further configured to:

receive additional data records from a user for sparse hyper-quadrants in the modeling space;

remove data records from dense hyper-quadrants in the modeling space;

or

create additional data records for sparse hyper-quadrants in the modeling space via a symmetric random scatter process.

15. The computer-based modeling system of claim 14, wherein to create the additional data records, the processor is further configured to:

determine starting ranges of the plurality of input parameters;

create a centroid data record including midpoint values of the starting ranges of the plurality of input parameters;

randomly create a plurality of sample data records of the input parameters within the starting ranges of the plurality of input parameters;

create a plurality of SRS data records of the sample data records as symmetric scatters of the plurality of sample data records with respect to the centroid data record;

create the additional data records by combining the centroid data record, the sample data records, and the SRS data records; and

remove the additional data records that fall out of the sparse hyper-quadrants.

16. The computer-based modeling system of claim 10, wherein the processor is further configured to:

statistically validate the computational model; and

optimize the computational model by maximizing a zeta statistic of the computational model.

17. A non-transitory computer-readable storage medium having stored thereon instructions which, when executed by a computer, cause the computer to perform a method for modifying data coverage in a modeling system, the method including:

obtaining data records relating to a plurality of input variables and one or more output parameters;

selecting a plurality of input parameters from the plurality of input variables;

evaluating a coverage of the data records in a modeling space by determining a data density of the data records in the modeling space, including;

dividing the modeling space into a plurality of hyper-quadrants; and

calculating the data density for each hyper-quadrant based on a number of data records in the respective hyper-quadrant;

detecting a data coverage condition based on the determined data density of the data records in the modeling space; and

when a data coverage condition is detected;

prompting a user of the modeling system to select from one of a plurality of methods for modifying the coverage of the data records;

receiving a selection from the user of one of the plurality of methods for modifying the coverage of the data records;

modifying the coverage of the data records according to the method selected by the user; and

generating a computational model indicative of interrelationships between a plurality of input parameters and the one or more output parameters based on the modified data records.

18. The computer readable medium of claim 17, wherein evaluating coverage of the data records further includes:

generating a histogram based on the calculated data densities of each hyper-quadrant;

determining a statistical difference in a data density distribution between the hyper-quadrants based on the generated histogram; and

identifying the data coverage condition when the statistical difference exceeds a first threshold.

19. The computer readable medium of claim 17, wherein the plurality of methods for modifying coverage of the data records further include at least two of:

receiving additional data records from a user for sparse hyper-quadrants in the modeling space;

removing data records from dense hyper-quadrants in the modeling space; and

creating additional data records for sparse hyper-quadrants in the modeling space via a symmetric random scatter process.

20. A method for modifying data coverage in a modeling computer system, comprising:

obtaining data records relating to a plurality of input variables and one or more output parameters;

dividing the data records into a plurality of hyper-quadrants in a modeling space;

determining, by a processor of the modeling computer system, data densities of the data records in the hyper-quadrants;

determining whether a data density of the data records in at least one of the hyper-quadrants is below a threshold; and

when a data density of the data records in at least one of the hyper-quadrants is below the threshold;

prompting a user of the modeling computer system to select a method to modify the data densities of the data records;

modifying the data densities of the data records, based on the method selected by the user, to increase the data density of the data records in the at least one hyper-quadrant or to decrease the data densities of the data records in at least one of the remaining hyper-quadrants; and

generating a computational model indicative of interrelationships between the plurality of input parameters and the one or more output parameters based on the modified data records.