{"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/traffic-state-data-imputation-an-efficient","title":"Traffic state data imputation: An efficient generating method based on the graph aggregator","arxiv_id":null,"date":"2022-08-12","proceeding":"IEEE Transactions on Intelligent Transportation Systems 2022 8","authors":["Dongwei Xu","Hang Peng","Chenchen Wei","Xuetian Shang","Haijian Li"],"abstract":"Road traffic state estimation is an essential component\r\nof intelligent transportation systems (ITSs). However,\r\nroad traffic state data collected by traffic detectors are often\r\nincomplete, which can cause problems across a variety of\r\ntransportation applications, such as traffic state prediction and\r\npattern recognition. We present GA-GAN (Graph Aggregate\r\nGenerative Adversarial Network), consisting of graph sample and\r\naggregate (GraphSAGE) and a generative adversarial network\r\n(GAN), to impute missing road traffic state data. Instead of\r\nusing the original road network structure, which presents the\r\nspatial information to process a graph operation, we reconstruct\r\nthe road network according to the correlation coefficients of\r\nroad historical data. We utilize GraphSAGE to aggregate the\r\ntemporal-spatial information from the neighbors of each road\r\nin the reconstructed road network. GAN is used to generate\r\ncomplete traffic state data from the extracted temporal-spatial\r\ninformation to achieve traffic state data imputation. To illustrate\r\nthe efficient performance of the model, experiments are\r\nconducted on traffic data collected from California and Seattle,\r\nWashington, showing that the proposed model outperforms stateof-the-art\r\nmethods.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9582618","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9582618","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":"traffic-state-data-imputation-an-efficient","repo_url":"https://github.com/pihang/GA-GAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"state-estimation","task_name":"State Estimation"},{"task_slug":"traffic-data-imputation","task_name":"Traffic Data Imputation"}],"methods":[{"method_slug":"graphsage","method_name":"GraphSAGE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}