System and method for trip classification

1. A method for classification of vehicle trip transportation modality comprising:

automatically detecting a vehicle trip associated with vehicular transportation of the mobile user device;

receiving a location dataset comprising location data collected with a location sensor of the mobile user device;

contemporaneously comparing the location dataset with a plurality of predetermined datasets, comprising:

determining a first plurality of features based on a first comparison between the location dataset and a railway dataset;

determining a second plurality of features based on a second comparison between the location dataset and a bus route dataset, wherein determining the second plurality of features comprises:

generating a plurality of candidate route segments based on the location dataset;

generating a plurality of candidate bus routes based on the plurality of candidate route segments;

pruning the set of candidate bus routes based on contextual information, wherein pruning a candidate bus route comprises eliminating the bus route from further consideration; and

determining the second plurality features based on the pruned set of candidate bus routes, wherein the second plurality of features comprises a score; and

determining a third plurality of features based on a third comparison between the location dataset and a roadway dataset;

classifying the vehicle trip based on the first, second, and third pluralities of features; and

based on the classification of the vehicle trip, triggering an action at the mobile user device.

2. The method of claim 1 , wherein the location dataset is received at a first time, wherein the action is triggered in substantially real time relative to the first time.

3. The method of claim 2 , wherein the first, second, and third pluralities of features are determined via separate, parallelized cloud computing processes.

4. The method of claim 1 , wherein classifying the vehicle trip comprises: classifying the vehicle trip as an off-road trip based on a satisfaction of a trip length condition and satisfaction of a respective probability condition for each of the first, second, and third pluralities of features.

5. The method of claim 1 , wherein the vehicle trip is classified with a machine-learning-based classification model.

6. The method of claim 1 , wherein classifying the vehicle trip comprises a multi-class classification using a heuristic, tree-based selection process.

7. The method of claim 6 , wherein classifying the vehicle trip comprises determining a decision parameter associated with a railway transportation class based on a joint probability associated with the first plurality of features and a differential comparison feature of the third plurality of features.

8. The method of claim 1 , wherein determining a second plurality of features comprises:

determining a set of stop locations based on the location dataset; and

comparing the stop locations to bus stops of the bus route dataset.

9. The method of claim 8 , wherein the score is determined based on a proximity of a trip end point to a bus stop.

10. The method of claim 1 , wherein the contextual information comprises: a direction of traversal on a roadway; and a route schedule.

11. The method of claim 1 , wherein the score comprises a dynamic time warping [DTW] similarity score, wherein determining the second plurality of features comprises: generating a candidate bus route comprising a series of route segments within the bus route dataset; and determining the DTW similarity score for the candidate bus route and the location dataset.

12. A method for classification of vehicle trip transportation modality comprising:

receiving a trip dataset for a vehicle trip associated with vehicular transportation of a mobile user device, the trip dataset comprising location data collected with a location sensor of the mobile user device;

determining a first set of features by comparing the trip dataset to a transit dataset, wherein determining the first set of features comprises determining a candidate bus route comprising a series of route segments using a bus route dataset, wherein determining the candidate bus route comprises:

generating a set of candidate route segments based on the trip dataset;

generating a set of candidate bus routes based on the set of candidate route segments;

selecting a candidate bus route from the set of candidate bus routes based on contextual information;

determining a second set of features by comparing the trip dataset to a roadway driving dataset;

based on the first and second sets of features, classifying the vehicle trip as an off- road vehicle trip; and

based on the classification of the vehicle trip as an off-road trip, triggering an action at the mobile user device.

13. The method of claim 12 , wherein classifying the vehicle trip as an off- road trip is further based on satisfaction of a minimum trip length associated with the trip dataset.

14. The method of claim 12 , wherein the first and second sets of features are each determined with a pretrained Hidden Markov Model (HMM).

15. The method of claim 12 , wherein the vehicle trip is classified as an off-road trip with a multi-class, tree-based classification model comprising a Bayesian network.

16. The method of claim 12 , wherein determining the first set of features comprises: determining a dynamic time warping [DTW] similarity score for the candidate bus route and the trip dataset, wherein the first set of features comprises the dynamic time warping [DTW] similarity score.

17. The method of claim 12 , wherein the vehicle trip is classified as an off-road vehicle trip by a heuristic, tree-based classification process.

18. The method of claim 17 , wherein classifying the vehicle trip as an off-road vehicle trip comprises determining a decision parameter associated with a railway transportation class based on a joint probability associated with the first set of features and a differential comparison feature of the second set of features.