A Framework for Information Aggregation and Predictions in Public Urban Bus Systems
Urban mobility through quality public transportation is one of the major challenges for the consolidation of smart cities. Researchers developed different approaches for improving bus system reliability and information quality, including travel time prediction algorithms, network state evaluations, and bus bunching prevention strategies. The information provided by these approaches is interdependent, and we could aggregate them for better predictions. In this work, we propose the architecture of a framework that enables the integration of several approaches into scalable and efficient composite models. For instance, travel time prediction models could use estimators of bus position, network state, bus headways, and other bus systems related information to deliver more accurate and reliable predictions. Here, we show the implementation of a prototype of the framework and evaluate its scalability, the CPU usage of the framework components, and the predictions of simple travel time models. We simulate real-time predictions and show that using this framework can be feasible in large metropolitan areas, such as São Paulo city. Last, we describe the final steps needed to conclude this work, including processing data collected in real-time and the proposal of more complex prediction algorithms.