| 主权项 |
1. A method for de-noising data in a scheduled transportation system, the method comprising:
receiving by a processor, a plurality of digital traces that correspond to a piece of equipment in the scheduled transportation system, wherein each of the plurality of digital traces are generated based on a determination that the corresponding piece of equipment has stopped; identifying by the processor a plurality of journeys from the plurality of digital traces, wherein each of the plurality of journeys corresponds to the piece of equipment traversing one of a plurality of routes; identifying by the processor a plurality of stops made by the piece of transportation equipment during each of the plurality of journeys; classifying by the processor, each of the plurality of identified stops into a type of stop, said classifying comprising: clustering by the processor, the plurality of stops along one of the plurality of routes into a set of potential stops; computing by the processor, a feature set for each of the set of potential stops; and classifying by the processor, each of the set of potential stops into the type of stop based on the feature set and a classification model, wherein the type of stop comprises at least one of a scheduled stop and a non-scheduled stop; identifying by the processor, a route map comprising at least a portion of the plurality of identified stops; identifying by the processor, a schedule for the scheduled transportation system; and updating by the processor, the route map and the schedule for the scheduled transportation system from the plurality of journeys and the plurality of digital traces. |
