Role detection in bicycle-sharing networks using multilayer stochastic block models

Abstract In urban systems, there is an interdependency between neighborhood roles and transportation patterns neighborhoods. this paper, we classify docking stations in bicycle-sharing networks to gain insight into the human mobility of three major cities United States. We propose novel time-dependent stochastic block models, with degree-heterogeneous blocks either mixed or discrete membership, which nodes based on their activity patterns. apply these models (1) detect (2) describe traffic within over course a day. Our successfully uncover work blocks, home other blocks; they also reveal that are specific each city. gives insights for design maintenance it contributes new methodology community detection temporal multilayer heterogeneous degrees.