{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-capsule-network-for-traffic-speed","title":"A Capsule Network for Traffic Speed Prediction in Complex Road Networks","arxiv_id":"1807.10603","date":"2018-07-23","proceeding":null,"authors":["Youngjoo Kim","Peng Wang","Yifei Zhu","Lyudmila Mihaylova"],"abstract":"This paper proposes a deep learning approach for traffic flow prediction in\ncomplex road networks. Traffic flow data from induction loop sensors are\nessentially a time series, which is also spatially related to traffic in\ndifferent road segments. The spatio-temporal traffic data can be converted into\nan image where the traffic data are expressed in a 3D space with respect to\nspace and time axes. Although convolutional neural networks (CNNs) have been\nshowing surprising performance in understanding images, they have a major\ndrawback. In the max pooling operation, CNNs are losing important information\nby locally taking the highest activation values. The inter-relationship in\ntraffic data measured by sparsely located sensors in different time intervals\nshould not be neglected in order to obtain accurate predictions. Thus, we\npropose a neural network with capsules that replaces max pooling by dynamic\nrouting. This is the first approach that employs the capsule network on a time\nseries forecasting problem, to our best knowledge. Moreover, an experiment on\nreal traffic speed data measured in the Santander city of Spain demonstrates\nthe proposed method outperforms the state-of-the-art method based on a CNN by\n13.1% in terms of root mean squared error.","url_abs":"http://arxiv.org/abs/1807.10603v2","url_pdf":"http://arxiv.org/pdf/1807.10603v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-capsule-network-for-traffic-speed","repo_url":"https://github.com/rhymesg/CapsNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"fixcaps","method_name":"Capsule Network"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}