Abstract
Passenger flow prediction has drawn increasing attention in the deep learning research field due to its great importance in traffic management and public safety. The major challenge of this essential task lies in multiple spatiotemporal correlations that exhibit complex non-linear correlations. Although both the spatial and temporal perspectives have been considered in modeling, most existing works have ignored complex temporal correlations or underlying spatial similarity. In this paper, we identify the unique spatiotemporal correlation of urban metro flow, and propose an attention-based deep spatiotemporal network with multi-task learning (ADST-Net) at a citywide level to predict the future flow from historical observations. ADST-Net uses three independent channels with the same structure to model the recent, daily-periodic and weekly-periodic complicated spatiotemporal correlations, respectively. Specifically, each channel uses the framework of residual networks, the rectified block and the multi-scale convolutions to mine spatiotemporal correlations. The residual networks can effectively overcome the gradient vanishing problem. The rectified block adopts an attentional mechanism to automatically reweigh measurements at different time intervals, and the multi-scale convolutions are used to extract explicit spatial relationships. ADST-Net also introduces an external embedding mechanism to extract the influence of external factors on flow prediction, such as weather conditions. Furthermore, we enforce multi-task learning to utilize transition passenger flow volume prediction as an auxiliary task during the training process for generalization. Through this model, we can not only capture the steady trend, but also the sudden changes of passenger flow. Extensive experimental results on two real-world traffic flow datasets demonstrate the obvious improvement and superior performance of our proposed algorithm compared with state-of-the-art baselines.
Highlights
With the rapid development of modern transportation, urban traffic congestion has become a commonplace phenomenon, which has brought a series of travel safety problems
Despite promising results on this single task, we argue that transition flows under the road map play a guiding role in traffic prediction, it is possible to capture underlying factors by jointly optimizing this related task
Different from the above-mentioned studies, we propose the attention-based deep spatial-temporal network with multi-task learning architecture (ADST-Net) for traffic flow prediction
Summary
With the rapid development of modern transportation, urban traffic congestion has become a commonplace phenomenon, which has brought a series of travel safety problems. More and more travelers are choosing underground transportation so as to avoid congestion on the ground In this case, metro flow prediction becomes an indispensable building component in data-driven urban computing to provide future reliable traffic guidance information, which will facilitate urban safety. A robust and accurate model is advised to be the basis of predicting urban metro flow to provide valuable warnings and deploy site security measures as early as possible. In this way, the city could mitigate congestion occurrence and improve metro utilization by means of big data and artificial intelligence technology [3]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
