Traffic flow prediction based on machine learning

Authors

  • Wenqi Zhang
  • Yixin Li

DOI:

https://doi.org/10.54097/sw3nmf68

Keywords:

Traffic Flow, K-means Algorithm, The Random Forest Regression Model.

Abstract

The rapid development of intelligent transportation systems requires accurate prediction of short-term traffic flow. However, the nonlinearity, uncertainty, and spatiotemporal variability of traffic flow make it difficult for traditional traffic flow prediction methods to achieve ideal results. This study uses machine learning methods to improve the accuracy of prediction and expand features by evaluating the clustering effect of the k-means algorithm through data dimensionality reduction, interpolation of missing data, and the silhouette coefficient method. The 5-fold cross-validation and grid search methods were used to optimize the hyperparameters, and the Lasso regression model, ridge regression model and random forest regression model were compared. It was found that the feature expansion of the random forest had the highest fitting coefficient and the smallest error. This improves prediction accuracy, provides a valuable reference for intelligent traffic flow prediction, and has the potential for further optimization in feature selection, model design, and traffic control strategies.

Downloads

Download data is not yet available.

References

[1] Liu Di. Research on safe operation of complex transportation networks based on several machine learning algorithms [D]. Southeast University, 2021.

[2] Xu Jianfeng, Tang Tao, Yan Junfeng, et al. Short-term traffic flow prediction based on multi-machine learning competition strategy [J]. Transportation System Engineering and Information, 2016, 16(04): 185-190+198.

[3] Jiang Xiaofeng, Xu Lunhui, Zhu Yue. Short-term traffic flow prediction based on SVM. "Journal of Guangxi Normal University" (Natural Science Edition), 2018, 30.4: 13-17.

[4] Du Jinbiao. Short-term traffic flow prediction based on CEEMD-RFR with improved KNN [D]. Chang'an University, 2018.

[5] Liu Yanli, Zhao Zhuofeng, Ding Weilong, et al. Short-term traffic flow prediction method based on high-speed toll big data [J]. Computers and Digital Engineering, 2019, 47(5):7.

[6] Wang Dexian, He Xianbo, He Chunlin, et al. Research on latent semantic prediction model combining L_1 and L_2 regularization constraints [J]. Computer Engineering and Applications, 2019, 55(19): 121-127.

[7] Wang Jiaqi, Hu Jingxin, Zhang Hongyan. Desert locust remote sensing monitoring based on machine learning [J]. Journal of Anhui Agricultural University, 2023, 50(04): 738-744.

[8] Jiao Pengpeng, An Yu, Bai Zixiu, et al. Research on short-term traffic flow prediction based on XGBoost [J]. Journal of Chongqing Jiaotong University (Natural Science Edition), 2022(008):041.

[9] Li Kunming, Gu Yijun, Wang An. Malicious PDF file detection technology under evasion attacks [J]. Journal of People's Public Security University of China: Natural Science Edition, 2019, 25(3):5.

[10] Liu Wei, Xu Wenfeng. Application of intelligent recommendation technology based on machine learning in transformer selection [J]. Electric Power Information and Communication Technology, 2019, 17(5): 19-24.

Downloads

Published

23-11-2024

How to Cite

Zhang, W., & Li, Y. (2024). Traffic flow prediction based on machine learning. Highlights in Science, Engineering and Technology, 118, 162-170. https://doi.org/10.54097/sw3nmf68