This study proposes a novel Graph Convolutional Neural Network with Data-driven Graph Filter (GCNN-DDGF) model that can learn hidden heterogeneous pairwise correlations between stations to predict station-level hourly demand in a large-scale bike-sharing network. Two architectures of the GCNN-DDGF model are explored; GCNNreg-DDGF is a regular GCNN-DDGF model which contains the convolution and feedforward blocks, and GCNNrec-DDGF additionally contains a recurrent block from the Long Short-term Memory neural network architecture to capture temporal dependencies in the bike-sharing demand series. Furthermore, four types of GCNN models are proposed whose adjacency matrices are based on various bikesharing system data, including Spatial Distance matrix (SD), Demand matrix (DE), Average Trip Duration matrix (ATD), and Demand Correlation matrix (DC). These six types of GCNN models and seven other benchmark models are built and compared on a Citi Bike dataset from New York City which includes 272 stations and over 28 million transactions from 2013 to 2016.Results show that the GCNNrec-DDGF performs the best in terms of the Root Mean Square Error, the Mean Absolute Error and the coefficient of determination (R 2 ), followed by the GCNNreg-DDGF. They outperform the other models. Through a more detailed graph network analysis based on the learned DDGF, insights are obtained on the "black box" of the GCNN-DDGF model. It is found to capture some information similar to details embedded in the SD, DE and DC matrices. More importantly, it also uncovers hidden heterogeneous pairwise correlations between stations that are not revealed by any of those matrices.
Variable message signs (VMS) are programmable traffic control devices that convey nonpersonalized real-time information on network traffic conditions to drivers encountering them. Especially useful under incidents, VMS aim to influence driver routing decisions to enhance network performance. This study investigates the effect of different message contents on driver response under VMS. Presumably, if the message content is a significant factor in driver response, the traffic controller can use it as a control variable to influence network traffic conditions positively without compromising the integrity of information. This issue is addressed through an on-site stated preference user survey. Logit models are developed for drivers’ diversion decisions. The analysis suggests that content in terms of the level of detail of relevant information significantly affects drivers’ willingness to divert. Other significant factors include socio-economic characteristics, network spatial knowledge, and confidence in the displayed information. Results also indicate differences in the response attitudes of semitrailer truck drivers compared to other travelers. They provide substantive insights for the design and operation of VMS-based information systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.