L. Meegahapola, N. Athaide, K. Jayarajah, S. Xiang and A. Misra, "Inferring Accurate Bus Trajectories from Noisy Estimated Arrival Time Records," 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, 2019, pp. 4517-4524.
Abstract:
Urban commuting data has long been a vital source of understanding population mobility behavior and has been widely adopted for various applications including transport infrastructure planning, anomaly detection, land use policy planning, etc. Whilst transaction records such as tap-in, tap-out data using smart fare cards from trains/buses, and individual trip records from public taxis hold a wealth of information, these are often private data available only to the service provider (e.g., taxicab operator). In this work, we explore the utility in harnessing publicly available, albeit noisy, transportation datasets, such as noisy “Estimated Time of Arrival” (ETA) records (commonly available to commuters through transit Apps, electronic signages, etc.). In this work, we first propose a framework to extract accurate individual bus trajectories from such ETA records and evaluate extensively using a real world dataset from Singapore. We further show that our findings are generalizable using a secondary dataset from a different metropolitan city (i.e., London). Finally, we report on the upper bound on the spatiotemporal resolution of the trajectory outputs that dictates the
resolution of the applications that consume such data.