Print Email Facebook Twitter Dynamic Graph Filters Networks Title Dynamic Graph Filters Networks: A Gray-box Model for Multistep Traffic Forecasting Author Li, G. (TU Delft Transport and Planning) Knoop, V.L. (TU Delft Transport and Planning) van Lint, J.W.C. (TU Delft Transport and Planning) Date 2020 Abstract Short-term traffic forecasting is one of the key functions in Intelligent Transportation System (ITS). Recently, deep learning is drawing more attention in this field. However, how to develop a deep learning based traffic forecasting model that can dynamically extract explainable spatial correlations from traffic data is still a challenging issue. The difficulty mainly comes from the inconsistency between static model structures and the dynamic evolution of traffic conditions. To overcome this difficulty, we proposed a novel multistep speed forecasting model, Dynamic Graph Filters Networks (DGFN). The major contribution is that the regular pixel-wise dynamic convolution is extended to graph topology. DGFN has a simple recurrent cell structure where local area-wide graph convolutional kernels are dynamically computed from varying inputs. Experiments on ring freeways show that DGFN is able to precisely predict short-term evolution of traffic speed. Furthermore, we theoretically explain why DGFN is not a pure “black-box”, but a “gray-box” model that actually reduces entangled spatial and temporal features into one component representing dynamic spatial correlations. It permits tracking real-time interactions among adjacent links. DGFN has the potential to relate trained parameters in deep learning models with physical traffic variables. To reference this document use: http://resolver.tudelft.nl/uuid:2db10787-ffa9-4744-9163-219ffb12e569 DOI https://doi.org/10.1109/ITSC45102.2020.9294627 Publisher IEEE Embargo date 2021-06-24 ISBN 978-1-7281-4150-3 Source 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) Event The 23rd IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2020), 2020-09-20 → 2020-09-23, Rhodes, Greece Series 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2020 G. Li, V.L. Knoop, J.W.C. van Lint Files PDF 09294627.pdf 1.73 MB Close viewer /islandora/object/uuid:2db10787-ffa9-4744-9163-219ffb12e569/datastream/OBJ/view