Research on traffic congestion prediction based on analyzable machine learning
DOI:
https://doi.org/10.54097/sbj3av77Keywords:
Pearson correlation coefficient, Decision Tree, Random Forest.Abstract
As motor vehicles proliferate around the world, traffic congestion increases, hindering travel, polluting the environment and hampering economic growth. Accurate congestion prediction is the key to optimizing traffic flow. In this study, the interaction between different traffic modes and congestion degree is deeply investigated, and a high-fidelity prediction model is established. The study analyses monthly, weekly, daily and hourly multi-modal traffic and congestion data and identifies congestion patterns. In this paper, Pearson's coefficient is applied to identify the key influencing factors, and congestion is predicted by KNN, logistic regression, decision tree and random forest models. The random forest model reaches 99.88% accuracy after 5-fold cross-validation and grid search optimisation. Further analysis using the Random Forest's feature importance scores revealed that traffic volume was the most important predictor of congestion, while time factors such as time and date played a smaller role. This study not only establishes a robust congestion prediction model, but also emphasizes the importance of traffic volume in congestion prediction. The findings provide valuable insights for traffic management agencies to take proactive measures to alleviate traffic congestion. By harnessing the predictive power of random forest models, these agencies can increase the efficiency of traffic management, improve the overall travel experience, and contribute to sustainable urban development. This study also lays a solid foundation for future research in the field of traffic congestion prediction and management.
Downloads
References
[1] Li Gang. Analysis of traffic congestion characteristics and improvement countermeasures on urban roads in Hohhot [J]. Traffic and Transport, 2024, 37(S1): 130-133.
[2] Zhao Jinlan. The role and mitigation strategy of intelligent transport system in traffic congestion based on big data algorithm analysis [J]. Electronic Components and Information Technology, 2024, 8(05): 86-88.
[3] Zheng Shujian, Yang Jingfeng. Research on the calculation method of traffic congestion evaluation index at home and abroad [J]. Highway and Motor Transport, 2014(1): 57-61.
[4] Lu Erkan, Rao Yao, Chen Zian. Analysis of traffic congestion characteristics of large cities in Zhejiang Province based on entropy weight TOPSIS method [J]. Transportation Science and Management, 2023, 4(21): 25-28.
[5] Tang Yi,Liu Weining, Sun Dihua, et al. Application of improved time series model in short-time traffic flow forecasting on highways [J]. Computer Application Research, 2015, 32(1): 146-150.
[6] Huang Helie, Cai Yanguang, Cai Hao, et al. Traffic flow clustering algorithm based on maximum deviation similarity criterion [J]. Computer Application Research, 2018, 35(8): 154-164.
[7] Bao Zhikang, Chen Jixuan, Liu Yinxiao, et al. Research on DNA sequence classification based on machine learning [J]. Biochemistry, 2024, 10(03): 20-27.
[8] Huang Yifeng, Wang Zhanhai. Research on civil aviation accident class classification model based on improved raccoon algorithm optimised random forest [J]. Journal of Civil Aviation, 2024,8(04): 109-113
[9] Li Sanjiang, Jiang Zhilin, Lin Yiwei, et al. A dynamic assessment method of metro communication system health based on random forest algorithm [J]. Urban Rail Transit Research, 2024, 27(06): 265-269+275.
[10] Hu Tingrui, Gao Yifan, Chen Li, et al. Analysis of GIS spatial analysis course assessment based on decision tree [J]. Geospatial Information, 2024, 22(08): 129-132.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.