Task description
Understanding human mobility is a key challenge in many fields, including transportation planning, epidemiology, and environmental science. Movement data is collected in various ways, including GPS data from smartphones, GPS trackers, or other devices.
A key insight into human movement is method of transport. This information often needs to be inferred, since its not provided by the device.
In this task, you will use movement data from the project by Zheng et al. (2011). The original dataset was collected in the GeoLife project (Microsoft Research Asia) by 182 users in a period of over three years (from April 2007 to August 2012). A GPS trajectory of this dataset is represented by a sequence of time-stamped points, each of which contains the information of latitude, longitude and altitude. This dataset contains 17’621 trajectories with a total distance of about 1.2 million kilometers and a total duration of 48,000+ hours. These trajectories were recorded by different GPS loggers and GPS-phones, and have a variety of sampling rates. 91 percent of the trajectories are logged in a dense representation, e.g. every 1~5 seconds or every 5~10 meters per point.
This dataset consists of a broad range of users’ outdoor movements, including not only life routines like go home and go to work but also some entertainments and sports activities, such as shopping, sightseeing, dining, hiking, and cycling.
The goal is to build a model that can predict the transportation mode of a trajectory based on the GPS data. To build this model, you will use the a labelled subset of the data:
73 users have labeled their trajectories with transportation mode, such as driving, taking a bus, riding a bike and walking. You will use these as labels, and build features to predict these labels from the movement parameters (such as speed, acceleration, sinuosity).