De-noising scheduled transportation data

• US 8,779,949 B2
• Filed: 10/30/2012
• Issued: 07/15/2014
• Est. Priority Date: 09/28/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bouillet, Eric P., Calabrese, Francesco, Pinelli, Fabio, Versheure, Olivier
• Primary Examiner(s): Algahaim, Helal A
• Assistant Examiner(s): CASTRO, PAUL A
• Application Number:
  US13/664,064
• Publication Number:
  US 20140094991A1
• Time in Patent Office: 623 Days
• Field of Search: None
• US Class Current: 340/994
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 10/083 Shipping
• CPC Class Codes: G06Q 10/08355 Routing methods
• CPC Class Codes: G06Q 50/30 Transportation; Communications
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083

Abstract

Embodiments of the disclosure include a method for de-noising data in a scheduled transportation system, the method includes receiving a plurality of digital traces that correspond to a piece of equipment in the scheduled transportation system. The method also includes identifying 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 and generating a route map and schedule for the scheduled transportation system from the plurality of journeys and the plurality of digital traces.

Claims

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.

2. The method of claim 1, wherein each of the plurality of digital traces comprises a location, a time-stamp, and an identification of the piece of equipment in the scheduled transportation system.

3. The method of claim 1, wherein classifying each of the set of potential stops includes calculating a confidence level.

4. The method of claim 1, wherein the classifying comprises applying a partial ground truth.

5. The method of claim 1, wherein the identification of the schedule includes the identification of the arrival times of the piece of transportation equipment at scheduled stops.

6. The method of claim 1, wherein updating the route map and schedule includes removing one or more scheduled stops from the route map and schedule.

7. The method of claim 1, wherein updating the route map and schedule includes adding one or more scheduled stops to the route map and schedule.

8. The method of claim 1, wherein updating the route map and schedule includes correcting a characteristic of one or more scheduled stops of the route map and schedule.

9. The method of claim 8, wherein the characteristics of a scheduled stop include at least one of a location, a list of lines serving the scheduled stop, a time of arrival of vehicles at the scheduled stop.