LEARNING TRANSPORTATION MODES FROM RAW GPS DATA
First Claim
1. In a computing environment, a method comprising:
- processing positioning data into a plurality of segments, the positioning data comprising location-related information and timing-related information;
determining a predicted mode of transportation for each segment.
2 Assignments
0 Petitions
Accused Products
Abstract
Described is a technology by which raw GPS data is processed into segments of a trip, with a predicted mode of transportation (e.g., walking, car, bus, bicycling) determined for each segment. The determined transportation modes may be used to tag the GPS data with transportation mode information, and/or dynamically used. Segments are first characterized as walk segments or non-walk segments based on velocity and/or acceleration. Features corresponding to each of those walk segments or non-walk segments are extracted, and analyzed with an inference model to determine probabilities for the possible modes of transportation for each segment. Post-processing may be used to modify the probabilities based on transitioning considerations with respect to the transportation mode of an adjacent segment. The most probable transportation mode for each segment is selected.
343 Citations
20 Claims
-
1. In a computing environment, a method comprising:
-
processing positioning data into a plurality of segments, the positioning data comprising location-related information and timing-related information; determining a predicted mode of transportation for each segment. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. In a computing environment, a system comprising:
-
a segmentation mechanism that separates GPS data into a plurality of segments; a feature extraction mechanism that extracts features for each segment; and an inference model that for each segment uses at least some of the features extracted for that segment to infer a transportation mode for that segment. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. One or more computer-readable media having computer-executable instructions, which when executed perform steps, comprising:
-
processing GPS data into walk segments and non-walk segments based on velocity data or acceleration data, or both velocity data and acceleration data; determining a length of each segment; comparing the lengths of the segments against a merge threshold distance, and merging any segment having a length below the threshold distance into another segment; comparing the lengths of the segments against a certainty threshold distance, and for any uncertain segments that do not meet the certainty threshold distance, determining whether a number of consecutive uncertain segments is present, and if so, merging the consecutive uncertain segments into a non-walk segment; and determining a predicted mode of transportation for each walk segment and for each non-walk segment, based on features of each segment. - View Dependent Claims (17)
-
-
18. The one or more computer-readable media of claim wherein predicting the mode of transportation comprises determining probabilities for candidate modes of transportation for each segment.
-
19. The one or more computer-readable media of claim wherein predicting the mode of transportation comprises, for at least one given segment, modifying at least some of the probabilities for candidate modes of transportation for that segment based on transition probability data corresponding to at least one adjacent segment, and selecting as the transportation mode for that segment the candidate transportation mode having a highest probability value after recalculation.
-
20. The one or more computer-readable media of claim having further computer-executable instructions comprising, tagging the GPS data with information corresponding to the predicted mode of transportation for each segment.
Specification