Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 01006 | |
Number of page(s) | 7 | |
Section | Traffic Prediction and Analysis | |
DOI | https://doi.org/10.1051/itmconf/20257001006 | |
Published online | 23 January 2025 |
The Relationship Between Traffic Flow Forecasting and Traffic Accident Forecasting and the Possible Combination Points
Department of Civil And Environmental Engineering, Hong Kong Polytechnic University, Hong Kong, 999077, China
Corresponding author: 24101879g@connect.polyu.hk
This paper mainly studies the relationship between traffic flow forecasting and traffic accident forecasting and the possible combination points. Firstly, through the introduction of the background, the necessity of combining the two is analyzed. Secondly, the differences between neural networks and traditional machine learning are compared in terms of model structure, feature extraction, applicability, computational resources and time, and model complexity'. This paper emphasizes the importance of neural networks for traffic flow forecasting and traffic accident forecasting and introduces the commonly used neural networks. Then, the concept of temporal and spatial characteristics in traffic data is expounded, which opens the relationship between traffic flow forecasting and traffic accident forecasting and the analysis of possible combination points. Through the analysis of the existing research, it is found that the relationship between the two is mainly divided mto data complementarity, common goal, and common method, and the possible combination points of the two are analyzed and prospected. Finally, the data and methods of improving traffic flow forecasting are summarized, which is conducive to better traffic flow forecasting and the combination of the two.
© 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.