Stationary classifier for geographic route trace data

1. A computer-implemented method for classifying activity of a device based upon data representing movement of the device, the method comprising:

receiving, by a device, a trace comprising a set of location data;

drawing a bounding box surrounding the trace, the bounding box corresponding to endpoints of the trace;

determining whether the trace is stationary by comparing a ratio between a length of the trace and a diagonal length of the drawn bounding box to a threshold value; and

responsive to determining the trace is non-stationary, extracting extremities from the trace for re-classifying.

2. The method of claim 1 , further comprising:

determining the threshold value using a classification function.

3. The method of claim 2 , further comprising:

receiving, by the device, a second trace known to be stationary; and

training the classification function using the second trace.

4. The method of claim 2 , wherein the classification function is a sigmoid function of the diagonal length of the drawn bounding box.

5. The method of claim 2 , wherein the classification function is modified by a set of factors comprising a geolocation factor.

6. The method of claim 1 , wherein the trace is classified as non-stationary if the ratio is greater than or equal to the determined threshold.

7. The method of claim 1 , wherein extracting extremities comprises identifying an outlier location data point in the set of location data that is beyond a threshold radius from an intermediate location data point in the set of location data.

8. The method of claim 1 , wherein the bounding box is drawn between two of an origin location data point, an intermediate location data point, and a destination location data point of the set of location data.

9. The method of claim 1 , wherein the bounding box is drawn between an origin location data point and a destination location data point of the set of location data.

10. The method of claim 1 , further comprising:

selecting an origin section for the trace, the origin section comprising an origin location data point and one or more intermediate location data points of the set of location data;

removing the origin section from the set of location data;

selecting a destination section for the trace, the destination section comprising a destination location data point and one or more of the intermediate location data points;

removing the destination section from the trace; and

dividing the trace into a plurality of subtraces, each subtrace comprising a plurality of consecutive intermediate location data points of the location data.

11. The method of claim 10 , further comprising:

removing, from each subtrace of the plurality of subtraces, one or more intermediate location data points connecting the subtrace to one or more other subtraces of the plurality of subtraces; and

storing each subtrace of the plurality of subtraces independently.

12. A non-transitory computer-readable storage medium storing computer program instructions executable by at least one processor, the computer program instructions comprising computer program instructions to:

receive, by a device, a trace comprising a set of location data;

draw a bounding box surrounding the trace, the bounding box corresponding to endpoints of the trace;

determine whether the trace is stationary by comparing a ratio between a length of the trace and a diagonal length of the drawn bounding box to a threshold value; and

responsive to determining the trace is non-stationary, extract extremities from the trace for re-classifying.

13. The non-transitory computer-readable storage medium of claim 12 , the computer program instructions further comprising computer program instructions to:

determine the threshold value using a classification function.

14. The non-transitory computer-readable storage medium of claim 13 , the computer program instructions further comprising computer program instructions to:

receive, by the device, a second trace known to be stationary; and

train the classification function using the second trace.

15. The non-transitory computer-readable storage medium of claim 13 , wherein the classification function is a sigmoid function of the diagonal length of the drawn bounding box.

16. The non-transitory computer-readable storage medium of claim 13 , wherein the classification function is modified by a set of factors comprising a geolocation factor.

17. The non-transitory computer-readable storage medium of claim 12 , wherein the bounding box is drawn between two of an origin location data point, an intermediate location data point, and a destination location data point of the set of location data.

18. The non-transitory computer-readable storage medium of claim 12 , the computer program instructions further comprising computer program instructions to:

select an origin section for the trace, the origin section comprising an origin location data point and one or more intermediate location data points of the set of location data;

remove the origin section from the set of location data;

select a destination section for the trace, the destination section comprising a destination location data point and one or more of the intermediate location data points;

remove the destination section from the trace; and

divide the trace into a plurality of subtraces, each subtrace comprising a plurality of consecutive intermediate location data points of the location data.

19. The non-transitory computer-readable storage medium of claim 18 , the computer program instructions further comprising computer program instructions to:

remove, from each subtrace of the plurality of subtraces, one or more intermediate location data points connecting the subtrace to one or more other subtraces of the plurality of subtraces; and

store each subtrace of the plurality of subtraces independently.