Modeling of incidents affecting quality of service of a transportation system
View Patent ↗A method and a device for predicting a future occurrence of a transportation system incident are disclosed. The method includes receiving transportation incident data comprising information collected during and related to operation of at least one transportation vehicle, the information comprising at least a time stamp, constructing at least one count regression model based upon the transportation incident data, producing a results set based upon the at least one count regression model, predicting at least one future occurrence of an incident based upon the results set, and presenting the at least one predicted future occurrence. The device includes at least a processing device and computer readable medium containing a set of instructions configured to cause the device to perform the method.
1. A method of predicting a future occurrence of a transportation system incident, comprising:
receiving, at a processing device, transportation incident data comprising information collected during and related to operation of at least one transportation vehicle, the information comprising at least a time stamp;
constructing, by the processing device, at least one count regression model based upon the transportation incident data;
producing, by the processing device, a results set based upon the at least one count regression model;
predicting, by the processing device, at least one future occurrence of an incident based upon the results set; and
presenting, by the processing device, the at least one predicted future occurrence.
2. The method of claim 1 , further comprising determining, by the processing device, a recommendation to add or remove a vehicle to a transportation system based upon the at least one predicted future occurrence.
3. The method of claim 1 , further comprising constructing, by the processing device, at least one contingency table based upon the transportation incident data.
4. The method of claim 1 , wherein the at least one count regression model comprises at least one of a Poisson log linear model, a zero inflated Poisson log linear model, a negative binomial log linear model, and a zero inflated negative binomial log linear model.
5. The method of claim 1 , further comprising displaying, at a display device operably connected to the processing device, the results set in a graphical user interface.
6. The method of claim 5 , wherein the presenting comprises:
merging the results set with a map; and
showing the results set are with the transportation incident data overlaid on a the map based on the locations corresponding to incidents represented by the data.
7. The method of claim 6 , further comprising altering the information displayed on the map in response to a user selection to view more information.
8. A device for predicting a future occurrence of a transportation system incident, the device comprising:
a processor; and
a computer readable medium operably connected to the processor, the computer readable medium containing a set of instructions configured to instruct the processor to perform the following:
receive transportation incident data comprising information collected during and related to operation of at least one transportation vehicle, the information comprising at least a time stamp,
construct at least one count regression model based upon the transportation incident data,
produce a results set based upon the at least one count regression model,
predict at least one future occurrence of an incident based upon the results set, and
present the at least one predicted future occurrence.
9. The device of claim 8 , wherein the set of instructions is further configured to instruct the processor to determine a recommendation to add or remove a vehicle to a transportation system based upon the at least one predicted future occurrence.
10. The device of claim 8 , wherein the set of instructions is further configured to instruct the processor to construct at least one contingency table based upon the transportation incident data.
11. The device of claim 8 , wherein the at least one count regression model comprises at least one of a Poisson log linear model, a zero inflated Poisson log linear model, a negative binomial log linear model, and a zero inflated negative binomial log linear model.
12. The device of claim 8 , wherein the set of instructions is further configured to instruct the processor to display, at a display device operably connected to the processing device, the results set in a graphical user interface.
13. The device of claim 12 , wherein the set of instructions configured to instruct the processor to display the results is further configured to instruct the processor to:
merge the results set with a map; and
show the results set are with the transportation incident data overlaid on a the map based on the locations corresponding to incidents represented by the data.
14. The device of claim 13 , wherein the set of instructions is further configured to instruct the processor to alter the information displayed on the map in response to a user selection to view more information.
15. A method of predicting a future occurrence of a transportation system incident for a transportation vehicle, comprising:
receiving, at a processing device, transportation incident data comprising information collected during and related to operation of the transportation vehicle, the information comprising at least a time stamp;
constructing, by the processing device, at least one contingency table based upon the transportation incident data;
constructing, by the processing device, at least one count regression model based upon the at least one contingency table;
producing, by the processing device, a results set based upon the at least one count regression model;
predicting, by the processing device, at least one future occurrence of an incident likely to effect the transportation vehicle based upon the results set;
presenting, by the processing device, the at least one predicted future occurrence likely to effect the transportation vehicle; and
altering at least a portion of the transportation system based upon the at least one predicted future occurrence to compensate for the at least one predicted future occurrence likely to effect the transportation vehicle.
16. The method of claim 15 , wherein altering at least a portion of the transportation system comprises determining, by the processing device, a recommendation to add or remove a vehicle to the transportation system.
17. The method of claim 15 , wherein the at least one count regression model comprises at least one of a Poisson log linear model, a zero inflated Poisson log linear model, a negative binomial log linear model, and a zero inflated negative binomial log linear model.
18. The method of claim 15 , further comprising displaying, at a display device operably connected to the processing device, the results set in a graphical user interface.
19. The method of claim 18 , wherein the presenting comprises:
merging the results set with a map; and
showing the results set are with the transportation incident data overlaid on a the map based on the locations corresponding to incidents represented by the data.
20. The method of claim 19 , further comprising altering the information displayed on the map in response to a user selection to view more information.