We recently developed a model for pedestrian activities from WiFi traces. The model uses triangulation data from a tool provided by Cisco. We have access to another dataset: the log data from the Radius server. Instead of triangulation, we only know the localization of the access point. First the data are less precise, but more than that, we don't know the confidence area (that was available for data provided by Cisco). The goal of this project would be first to adapt the code for this new dataset, analyze the results, and compare them with results from triangulation data. Second, the code is currently asking a postgresql database on the server to compute the shortest path. The student is supposed to code the shortest path directly in Python. Third, some calibration would be part of the project. Finally, the students is supposed to visualize the results in a nice way. Visualization is fully part of this project.
To know more about it, contact me.