Data of urban public transport networks was collected, to fulfil the requirements specifications of the system. This not only includes data from traffic and meteorology sensors, but also instruments that collect and provide data. The data collected will not only enable the team to extract knowledge from the network, but also to validate the developed tools.

A platform based on big data technologies was designed and partially implemented, to support not only the data collection but also the knowledge extraction, visualization and optimization (see figure bellow). Several data flow processes were defined, implemented and executed, for collecting data from the Internet. These data include geospatial information (infrastructures and points of interest), traffic flows and road conditions, meteorology, air quality, and public transport (network information and geolocation records).