Generating On-Demand Mobility Data for Urban Vehicles Based on Bus Aggregated Data

On-demand mobility in urban areas is gaining increasing attention from researchers nowadays. However, human mobility data availability is a real challenge for experiments, because of privacy and commercial concerns, as well as the high cost to deploy sensors and a long time to collect the data. Thus, plausible mobility data generation is an acceptable solution for researchers to conduct their experiments. In this study, we propose a model for generating a set of plausible on-demand mobility requests data from an urban bus aggregated data. A three-step method is introduced to perform data generation for each bus trip. First, the plausible arrival date is computed for every bus stop by using data from OpenStreetMap¹¹https://www.openstreetmap.org. In the second step, the total number of passengers served by the trip is distributed appropriately on the stops. At the third and final step, individual passenger requests are generated from each bus stop, using previous results and, a temporal and spatial uniform distribution. The experiments, conducted using the bus company SOTRAL²²http://sotraltogo.com/ data as source shows that the generated data fits quite well with the activity density levels of the different city areas. A multiplication factor introduced even allows to generate more or less demands than in the source dataset.