Urban Arterial Road Traffic Flow Prediction Based on NRBO-XGBoost.
Saved in:
| Title: | Urban Arterial Road Traffic Flow Prediction Based on NRBO-XGBoost. |
|---|---|
| Authors: | Zeng, Junwei1 zengjunwei@mail.lzjtu.cn, Zhao, Tongchang2 12241100@stu.lzjtu.edu.cn, Qian, Yongsheng1 qianyongsheng@mail.lzjtu.cn, He, Qingling3 qinglinghe@lzjtu.edu.cn, Wei, Xu3 weixt@mail.lzjtu.cn |
| Source: | IAENG International Journal of Applied Mathematics. May2026, Vol. 56 Issue 5, p1871-1878. 8p. |
| Subjects: | Machine learning, Iterative methods (Mathematics), Pearson correlation (Statistics), Traffic congestion, Traffic estimation, Roads |
| Abstract: | To mitigate traffic congestion and travel time costs on urban arterial roads and enhance the accuracy and applicability of traffic flow prediction, this study developed a traffic flow forecasting model for urban trunk roads based on Newton-Raphson algorithm-optimized XGBoost (NRBO-XGBoost), which utilizes traffic flow data from the normal, post-construction recovery, and construction phases; first, the Pearson correlation coefficient was employed to analyze the influence of factors including travel speed, number of lanes, vehicle mix rate, and non-motorized vehicle volume on traffic flow across different periods, and the results indicate that the correlation coefficients of these factors range from -0.12 to 0.45 in the normal phase, -0.16 to 0.49 in the recov ery phase, and -0.22 to 0.49 in the construction phase; the NRBO-XGBoost model achieves optimal performance when the number of iterations and population size are set to 30 and 40, respectively, and the fitting curves between actual and predicted traffic flow values demonstrate high accuracy, with R² values of 0.9833, 0.9830, and 0.9822 for the normal, recovery, and construction periods, respectively; moreover, the mean absolute percentage error (MAPE) of the NRBO-XGBoost model in these three periods is 7.81%, 8.24%, and 8.75%, respectively, representing reductions of 2.2-6.41%, 2.44-6.15%, and 1.94-6.04% compared to the WOA-XGBoost, PSO-XGBoost, XGBoost, LSTM, and GRU models, and these findings can assist in formulating urban traffic guidance and congestion mitigation strategies, thereby improving the service level and operational efficiency of urban transportation systems. [ABSTRACT FROM AUTHOR] |
| Copyright of IAENG International Journal of Applied Mathematics is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
