Authenticating drivers

1. A method, comprising:

receiving, by a computing device, global positioning system (GPS) data collected by a user device during a driving trip;

analyzing the GPS data to determine a plurality of time-series data, wherein each time-series data comprises data corresponding to a different physical parameter reflected in the GPS data;

dividing each of the plurality of time-series data into a plurality of overlapping window frames of a predetermined length;

for each of the plurality of overlapping window frames, analyzing corresponding data for the window frame to determine a first probability score reflecting a probability that the window frame comprises driver trip data and a second probability score reflecting a probability that the window frame comprises non-driver trip data;

calculating, using the first probability scores for each of the plurality of overlapping window frames, a first total probability score reflecting a probability that the driving trip comprises driver-trip data;

calculating, using the second probability scores for each of the plurality of overlapping window frames, a second total probability score reflecting a probability that the driving trip comprises non-driver trip data; and

identifying a user of the user device as a driver of the driving trip, based on a comparison of the first total probability score and the second total probability score.

2. The method of claim 1 , wherein the data corresponding to the different physical parameter reflected in the GPS data is reflective of at least one of: a steering wheel angle, a gas pedal position, and a brake pedal position, and

wherein the physical parameter comprises at least one of: speed, course, acceleration, jerk, angular speed, angular acceleration, angular jerk, and power per mass ratio.

3. The method of claim 1 , wherein the GPS data comprises speed data and course data, and

wherein the method further comprises calculating, using the speed data and the course data, acceleration, jerk, angular speed, angular acceleration, angular jerk, and power per mass ratio.

4. The method of claim 1 , wherein the predetermined length of the plurality of overlapping window frames is between approximately 30 and 50 seconds, and

wherein an overlapping portion of consecutive window frames, of the plurality of overlapping window frames, comprises approximately one-third of the predetermined length.

5. The method of claim 1 , wherein analyzing the corresponding data for the window frame to determine the first probability score and the second probability score comprises:

extracting, from the corresponding data for the window frame, statistical, dynamic, and spectral features of the corresponding data;

generating, using the extracted features of the corresponding data, a feature vector for the window frame; and

determining a trip state associated with the feature vector for the window frame, wherein the trip state comprises at least one of: a road type, a traffic condition, and a driving maneuver.

6. The method of claim 5 , further comprising:

retrieving a driver probability profile associated with the user of the user device;

comparing the feature vector for the window frame to a portion of the driver probability profile determined to correspond to the determined trip state associated with the feature vector for the window frame; and

generating, based on the comparison, the first probability score.

7. The method of claim 5 , further comprising:

retrieving an average driver probability profile associated with an average driver, wherein the average driver probability profile represents an average of all known driving profiles;

comparing the feature vector for the window frame to a portion of the average driver probability profile determined to correspond to the determined trip state associated with the feature vector for the window frame; and

generating, based on the comparison, the second probability score.

8. The method of claim 1 , wherein identifying the user of the user device as the driver comprises:

identifying the user of the user device as the driver of the driving trip based on determining that the first total probability score is greater than the second total probability score.

9. A computing device, comprising:

a processor; and

memory storing computer-executable instructions that, when executed by the processor, cause the computing device to:

receive global positioning system (GPS) data collected by a user device during a driving trip;

analyze the GPS data to determine a plurality of time-series data, wherein each time-series data comprises data corresponding to a different physical parameter reflected in the GPS data;

divide each of the plurality of time-series data into a plurality of overlapping window frames of a predetermined length;

for each of the plurality of overlapping window frames, analyze corresponding data for the window frame to determine a first probability score reflecting a probability that the window frame comprises driver trip data and a second probability score reflecting a probability that the window frame comprises non-driver trip data;

calculate, using the first probability scores for each of the plurality of overlapping window frames, a first total probability score reflecting a probability that the driving trip comprises driver trip data;

calculate, using the second probability scores for each of the plurality of overlapping window frames, a second total probability score reflecting a probability that the driving trip comprises non driver trip data; and

identify a user of the user device as a driver of the driving trip, based on a comparison of the first total probability score and the second total probability score.

10. The computing device of claim 9 , wherein the data corresponding to the different physical parameter reflected in the GPS data is reflective of at least one of: a steering wheel angle, a gas pedal position, and a brake pedal position, and

wherein the physical parameter comprises at least one of: speed, course, acceleration, jerk, angular speed, angular acceleration, angular jerk, and power per mass ratio.

11. The computing device of claim 9 , wherein the GPS data comprises speed data and course data, and

wherein the computer-executable instructions, when executed by the processor, further cause the computing device to calculate, using the speed data and the course data, acceleration, jerk, angular speed, angular acceleration, angular jerk, and power per mass ratio.

12. The computing device of claim 9 , wherein the computer-executable instructions, when executed by the processor, further cause the computing device to analyze the corresponding data for the window frame to determine the first probability score and the second probability score by:

extracting, from the corresponding data for the window frame, statistical, dynamic, and spectral features of the corresponding data;

generating, using the extracted features of the corresponding data, a feature vector for the window frame; and

determining a trip state associated with the feature vector for the window frame, wherein the trip state comprises at least one of: a road type, a traffic condition, and a driving maneuver.

13. The computing device of claim 12 , wherein the computer-executable instructions, when executed by the processor, further cause the computing device to:

retrieve a driver probability profile associated with the user of the user device;

compare the feature vector for the window frame to a portion of the driver probability profile determined to correspond to the determined trip state associated with the feature vector for the window frame; and

generate, based on the comparison, the first probability score.

14. The computing device of claim 12 , wherein the computer-executable instructions, when executed by the processor, further cause the computing device to:

retrieve an average driver probability profile associated with an average driver, wherein the average driver probability profile represents an average of all known driving profiles;

compare the feature vector for the window frame to a portion of the average driver probability profile determined to correspond to the determined trip state associated with the feature vector for the window frame; and

generate, based on the comparison, the second probability score.

15. The computing device of claim 9 , wherein the computer-executable instructions, when executed by the processor, further cause the computing device to identify the user of the user device as the driver of the driving trip based on determining that the first total probability score is greater than the second total probability score.

16. A non-transitory, computer-readable storage medium storing instructions that, when executed by a processor of a computing device, cause the computing device to:

receive global positioning system (GPS) data collected by a user device during a driving trip;

analyze the GPS data to determine a plurality of time-series data, wherein each time-series data comprises data corresponding to a different physical parameter reflected in the GPS data;

divide each of the plurality of time-series data into a plurality of overlapping window frames of a predetermined length;

for each of the plurality of overlapping window frames, analyze corresponding data for the window frame to determine a first probability score reflecting a probability that the window frame comprises driver trip data and a second probability score reflecting a probability that the window frame comprises non-driver trip data;

calculate, using the first probability scores for each of the plurality of overlapping window frames, a first total probability score reflecting a probability that the driving trip comprises driving driver trip data;

calculate, using the second probability scores for each of the plurality of overlapping window frames, a second total probability score reflecting a probability that the driving trip comprises non-driving driver trip data; and

identify a user of the user device as a driver of the driving trip, based on a comparison of the first total probability score and the second total probability score.

17. The non-transitory, computer-readable storage medium of claim 16 , wherein the data corresponding to the different physical parameter reflected in the GPS data is reflective of at least one of: a steering wheel angle, a gas pedal position, and a brake pedal position,

wherein the physical parameter comprises at least one of: speed, course, acceleration, jerk, angular speed, angular acceleration, angular jerk, and power per mass ratio, and

wherein the instructions, when executed by the processor of the computing device, further cause the computing device to calculate, using speed data and course data from the GPS data, the acceleration, the jerk, the angular speed, the angular acceleration, the angular jerk, and the power per mass ratio.

18. The non-transitory, computer-readable storage medium of claim 16 , the instructions, when executed by the processor of the computing device, further cause the computing device to analyze the corresponding data for the window frame to determine the first probability score and the second probability score by:

extracting, from the corresponding data for the window frame, statistical, dynamic, and spectral features of the corresponding data;

generating, using the extracted features of the corresponding data, a feature vector for the window frame; and

determining a trip state associated with the feature vector for the window frame, wherein the trip state comprises at least one of: a road type, a traffic condition, and a driving maneuver.

19. The non-transitory, computer-readable storage medium of claim 18 , wherein the instructions, when executed by the processor of the computing device, further cause the computing device to:

retrieve a driver probability profile associated with the user of the user device;

compare the feature vector for the window frame to a portion of the driver probability profile determined to correspond to the determined trip state associated with the feature vector for the window frame;

generate, based on the comparison, the first probability score;

retrieve an average driver probability profile associated with an average driver, wherein the average driver probability profile represents an average of all known driving profiles;

compare the feature vector for the window frame to a portion of the average driver probability profile determined to correspond to the determined trip state associated with the feature vector for the window frame; and

generate, based on the comparison, the second probability score.

20. The method of claim 1 , wherein analyzing the GPS data to determine the plurality of time-series data comprises analyzing the GPS data after the driving trip has ended.