Methods and systems for sensor-based driving data collection
A system for collecting vehicle data includes a mobile device comprising a plurality of sensors, a memory, and a processor coupled to the memory. The processor is configured to perform operations including obtaining a plurality of movement measurements from at least one of the plurality of sensors in the mobile device, determining a plurality of transportation modes using the plurality of movement measurements, and determining a mode transition using the plurality of transportation modes. The operations also include determining a transition probability using the mode transition. The operations further include creating a transition model using the transition probabilities, determining that the transition model indicates that a probability that the second transportation mode comprises driving is above a threshold, obtaining a plurality of driving movement measurements from at least one of the plurality of sensors, and determining the vehicle data using the driving movement measurements.
1. A system for collecting vehicle data, the system comprising:
a mobile device of a user comprising a plurality of sensors;
a memory; and
a processor coupled to the memory, wherein the processor is configured to perform operations including:
obtaining a plurality of movement measurements from at least one of the plurality of sensors in the mobile device;
determining a plurality of transportation modes using the plurality of movement measurements;
determining a mode transition using the plurality of transportation modes, the mode transition being associated with a change from a first transportation mode of the plurality of transportation modules to a second transportation mode of the plurality of transportation modes;
determining a transition probability using the mode transition, the transition probability being associated with a probability of a change from the first transportation mode to the second transportation mode;
creating a transition model using the transition probability;
determining that the transition model indicates that a probability that the user of the mobile device is driving is above a threshold, wherein the probability indicates a likelihood that the second transportation mode comprises driving by the user of the mobile device;
obtaining a plurality of driving movement measurements from at least one of the plurality of sensors, wherein the obtaining the plurality of driving movement measurements from the at least one of the plurality of sensors comprises:
selecting a sample time based on the transition model;
determining, at the sample time, the probability that the second transportation mode comprises driving by the user of the mobile device using the transition model;
selecting a testing interval when the probability that the second transportation mode comprises driving by the user of the mobile device is above the threshold; and
controlling the at least one of the plurality of sensors to obtain the plurality of driving movement measurements at the testing interval while the probability that the second transportation mode comprises driving by the user of the mobile device is above the threshold; and
determining the vehicle data using the plurality of driving movement measurements to track a driving behavior of the user of the mobile device.
2. The system of claim 1 , wherein the operations further include updating the transition model using the driving movement measurements.
3. The system of claim 1 , wherein the operations further include receiving contextual data related to a transportation system, wherein the determining the plurality of transportation modes includes determining the plurality of transportation modes using the contextual data.
4. The system of claim 3 , wherein the contextual data comprises at least one of schedules and route data for trains and buses.
5. The system of claim 1 , wherein the plurality of sensors comprise a gyroscope, an accelerometer, and a GPS.
6. The system of claim 1 , wherein the determining the transition probability comprises using a transition pattern associated with the mobile device.
7. The system of claim 1 , wherein the determining the plurality of transportation modes comprises determining a Fourier frequency of a subset of the plurality of movement measurements.
8. The system of claim 1 , wherein the operations further include:
deactivating the at least one of the plurality of sensors when the probability that the second transportation mode comprises driving by the user of the mobile device is below the threshold.
9. A method for collecting vehicle data, the method comprising:
obtaining a plurality of movement measurements from at least one of the plurality of sensors in the mobile device;
determining a plurality of transportation modes using the plurality of movement measurements;
determining a mode transition using the plurality of transportation modes, the mode transition being associated with a change from a first transportation mode of the plurality of transportation modules to a second transportation mode of the plurality of transportation modes;
determining a transition probability using the mode transition, the transition probability being associated with a probability of a change from the first transportation mode to the second transportation mode;
creating a transition model using the transition probability;
determining that the transition model indicates that a probability that the user of the mobile device is driving is above a threshold, wherein the probability indicates a likelihood that the second transportation mode comprises driving by the user of the mobile device;
obtaining a plurality of driving movement measurements from at least one of the plurality of sensors, wherein the obtaining the plurality of driving movement measurements from the at least one of the plurality of sensors comprises:
selecting a sample time based on the transition model;
determining, at the sample time, the probability that the second transportation mode comprises driving by the user of the mobile device using the transition model;
selecting a testing interval when the probability that the second transportation mode comprises driving by the user of the mobile device is above the threshold; and
controlling the at least one of the plurality of sensors to obtain the plurality of driving movement measurements at the testing interval while the probability that the second transportation mode comprises driving by the user of the mobile device is above the threshold; and
determining the vehicle data using the plurality of driving movement measurements to track a driving behavior of the user of the mobile device.
10. The method of claim 9 , further comprising updating the transition model using the driving movement measurements.
11. The method of claim 9 , wherein the operations further include receiving contextual data related to a transportation system, wherein the determining the plurality of transportation modes includes determining the plurality of transportation modes using the contextual data.
12. The method of claim 11 , wherein the contextual data comprises at least one of schedules and route data for trains and buses.
13. The method of claim 9 , wherein the plurality of sensors comprise a gyroscope, an accelerometer, and a GPS.
14. The method of claim 9 , wherein the determining the transition probability comprises using a transition pattern associated with the mobile device.
15. The method of claim 9 , wherein the determining the plurality of transportation modes comprises determining a Fourier frequency of a subset of the plurality of movement measurements.
16. The method of claim 9 , further comprising:
deactivating the at least one of the plurality of sensors when the probability that the second transportation mode comprises driving by the user of the mobile device is below the threshold.