Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 01011 | |
Number of page(s) | 9 | |
Section | Traffic Prediction and Analysis | |
DOI | https://doi.org/10.1051/itmconf/20257001011 | |
Published online | 23 January 2025 |
The Application Prospects of Event Data in Traffic Flow Prediction
1 College of Computer Science and Technology, Civil Aviation University of China, Tianjin, 300000, China
2 School of Management, Hefei University of Technology, Hefei, Anhui, 230009, China
3 Shijiazhuang New Century Foreign Language School, Shijiazhuang, Hebei, 050000, China
* Corresponding author: 220340049@cauc.edu.cn
Conventional methods of predicting traffic flow can often be based on weekdays, certain holidays, road conditions, or signal light circumstances. Nevertheless, because there isn’t always an impact study done for some exceptional occurrences, these forecasting techniques or models might be ineffective. Recent studies have pointed out that social events such as concerts and large-scale events have a huge impact on Traffic flow. Considering these social events, to more accurately predict Traffic flow, this article refers to previous relevant literature, comprehensively describes the significant improvement of event data in traffic flow prediction (TFP) and how to use it, and generally discusses the relevant models that may apply event data to TFP. In detail, the current research results on STG-NCDE and Bi-LSTM models are presented, and the correlation, advantages, and disadvantages of the two are compared. In addition, the problems and challenges faced by the current application of event data in TFP are innovatively analyzed and discussed. Finally, the further achievements and related technology development trends that may be made in TFP based on this research direction in the prospect, and the article is summarized.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.