STTBoost: A Hybrid Road Traffic Congestion Prediction Model Using Transformer and XGBoost
Keywords:
Traffic congestion prediction, Free-stream velocity, Number of vehicles, Geohash-temporal information, Transformer, XGBoost.Abstract
Accurate traffic congestion prediction is crucial for effectively managing urban transportation systems. Traditional models often focus on either speed or density factors independently, which limits their ability to capture the complex dynamics of real-world traffic conditions. This paper proposes a hybrid approach that integrates both speed and density factors to enhance the realism and accuracy of congestion prediction. The standard TCI is modified to combine density with speed, and a modified Traffic Congestion Index (M_TCI) is proposed. A new hybrid model called STTBoost (Spatio-temporal Transformer Boost) is also proposed, which uses the strengths of Transformer networks and XGBoost to predict traffic congestion. The Transformer model captures spatial-temporal dependencies, whereas XGBoost excels at handling nonlinear patterns. The integration of these two models is used for robust predictions, especially when contextual features, such as road characteristics, road incidents, and temporal patterns, are included. The proposed hybrid model, tested on real-world datasets, demonstrates significant improvements in prediction accuracy, offering a powerful tool for modern traffic management systems. This approach addresses the shortcomings of existing models by providing a more comprehensive and realistic method for congestion forecasting.
Downloads
References
Alghamdi, T., Elgazzar, K., Bayoumi, M., Sharaf, T., Shah, S.: Forecasting traffic congestion using ARIMA modeling. In 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC). IEEE, pp. 1227–1232 (2019)
Zaki, J.F., Ali-Eldin, A.M., Hussein, S.E., Saraya, S.F., Areed, F.F.: Time aware hybrid hidden Markov models for traffic congestion prediction. Int. J. Elect. Eng. Inform. 11(1), 1–17 (2019)
Wen, F., Zhang, G., Sun, L., Wang, X., Xu, X.: A hybrid temporal association rules mining method for traffic congestion prediction. Comput. Ind. Eng. 130, 779–787 (2019)
Chen, F., Chen, Z., Biswas, S., Lei, S., Ramakrishnan, N., & Lu, C. T. (2020, November). Graph convolutional networks with kalman filtering for traffic prediction. In Proceedings of the 28th international conference on advances in geographic information systems (pp. 135-138).
Momin, Khondhaker Al, et al. "Short duration traffic flow prediction using kalman filtering." AIP Conference Proceedings. Vol. 2713. No. 1. AIP Publishing, 2023.
Majumdar, Sharmila, et al. "Congestion prediction for smart sustainable cities using IoT and machine learning approaches." Sustainable Cities and Society 64 (2021): 102500.
Akhtar, M., Moridpour, S.: A review of traffic congestion prediction using artificial intelligence. J. Adv. Transport. 2021, 8878011 (2021)
Al Jawarneh, Isam Mashhour, Luca Foschini, and Paolo Bellavista. "Polygon simplification for the efficient approximate analytics of georeferenced big data." Sensors 23.19 (2023): 8178.
Yin, F.; Chen, H. Geohash encoding of k-anonymous location privacy protection scheme. J. Wuhan Univ. Sci. Ed. 2022, 68, 73–82.
Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N; Kaiser, Łukasz; Polosukhin, Illia (2017). "Attention is All you Need" (PDF). Advances in Neural Information Processing Systems. 30. Curran Associates, Inc.
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo,B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10012–10022 (2021)
Lim, B., Arık, S.Ö., Loeff, N., Pfister, T.: Temporal fusion transformers for interpretable multi-horizon time series forecasting.Int. J. Forecast. 37(4), 1748–1764 (2021)
Ahmed, Shams Forruque, et al. "Deep learning modelling techniques: current progress, applications, advantages, and challenges." Artificial Intelligence Review 56.11 (2023): 13521-13617.
Alghamdi, A.S., et al. "Short-term traffic prediction using ARIMA-LSTM hybrid model." Transportation Research Record (2021).
Giraka, Omkar, and Vasantha Kumar Selvaraj. "Short-term prediction of intersection turning volume using seasonal ARIMA model." Transportation letters 12.7 (2020): 483-490.
Kamaruddin, S. et al. "Using support vector machines for traffic congestion prediction with weather data." Journal of Advanced Transportation (2022).
Xu, M., et al. "Random Forest ensemble learning for accurate traffic congestion prediction." IEEE Transactions on Intelligent Transportation Systems (2021).
Zhou, L., et al. "XGBoost-based congestion prediction for intelligent transportation systems." Applied Sciences (2023).
Yang, H., et al. "LSTM-based traffic congestion prediction using temporal patterns." Journal of Big Data Analytics in Transportation (2022).
Zhu, Y., et al. "A hybrid CNN-LSTM model for traffic congestion prediction in urban areas." IEEE Access (2021).
Li, Z., et al. "GNN-based traffic congestion prediction using road network structure." Journal of Transportation Engineering (2022).
Wang, X., et al. "STTF: A spatio-temporal transformer model for traffic congestion prediction." International Journal of Computational Intelligence Systems (2023).
HCM 2010: Highway Capacity Manual. Washington, D.C.: Transportation Research Board, 2010.
Tanberk, Senem, Mustafa Can, and Selahattin Serdar Helli. "Smart Journey in Istanbul: A Mobile Application in Smart Cities for Traffic Estimation by Harnessing Time Series." 2023 Innovations in Intelligent Systems and Applications Conference (ASYU). IEEE, 2023.
Omran, Saleh, Ibtisam Masmali, and Ghaliah Alhamzi. "Banach fixed point theorems in generalized metric space endowed with the Hadamard product." Symmetry 15.7 (2023): 1325.
Arifoğulları, Ömer, and Gülfem Işıklar Alptekin. "Public Transportation Data Analysis to Estimate Road Status in Metropolitan Areas: The Case of İstanbul." Procedia Computer Science 210 (2022): 12-18.
Ma, J., Yarats, D.: On the adequacy of untuned warmup for adaptive optimization. arXiv preprint 7. arXiv: 1910. 04209 (2019)
Liu, Liyuan, et al. "Understanding the difficulty of training transformers." arXiv preprint arXiv:2004.08249 (2020).
Alghamdi, T., Elgazzar, K., Bayoumi, M., Sharaf, T., Shah, S.:Forecasting traffic congestion using ARIMA modeling. In 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC). IEEE, pp. 1227–1232 (2019)
Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. arXiv preprint arXiv: 1707. 01926 (2017)
Shin, Dong-Hoon, Kyungyong Chung, and Roy C. Park. "Prediction of traffic congestion based on LSTM through correction of missing temporal and spatial data." IEEE Access 8 (2020): 150784-150796.
Zheng, Chuanpan, et al. "Gman: A graph multi-attention network for traffic prediction." Proceedings of the AAAI conference on artificial intelligence. Vol. 34. No. 01. 2020.
Liang, Jiaqi. "A method for the detection of electricity theft behavior based on Xavier weight initialization." Second International Conference on Electronic Information Technology (EIT 2023). Vol. 12719. SPIE, 2023.
Zhan, Q. L., and Y. Li. "An evaluation method for economic loss of urban road traffic: XGboost algorithm." Advances in transportation studies (2023).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Deepti Soni, Shraddha Masih
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
