Traffic flow prediction using adaptive graph convolutional networks and long short-term memory
,
,
and
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
Traffic congestion is becoming an increasingly serious and challenging issue in major urban areas. This problem not only causes a waste of time and increased fuel consumption but also contributes to environmental pollution and deterioration of residents’ quality of life. In this study, a new method of predicting the average speed reported by traffic sensors across the city was proposed. In this method, we make the most of two core models: Graph Convolutional Networks and Long Short-Term Memory. The YOLO model is used to analyze images and video during data collection. By leveraging Graphe Convolution Networks ability to capture spatial information, Long Short-Term Memory capacity to model temporal dynamics, and YOLO’s strength in visual object detection, our integrated framework enhances the accuracy of traffic flow predictions at specific locations and time intervals. This comprehensive approach aims to support real-world applications such as adaptive traffic light control, traffic planning support, and congestion alerts. The proposed method outperforms other methods on the Caltrans PeMS dataset.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Awan, F. M., Minerva, R., & Crespi, N. (2020). Improving road traffic forecasting using air pollution and atmospheric data: Experiments based on LSTM recurrent neural network. Sensors, 20(13), 3749. https://doi.org/10.3390/s20133749
Bengio, Y., Frasconi, P., & Simard, P. (2002 Aug 06). The problem of learning long-term dependencies in recurrent networks. In IEEE International Conference on Neural Networks, San Francisco, CA, USA (pp. 1183-1188) https://ieeexplore.ieee.org/document/298725).
Caltrans. (n.d.). Source performance measurement system data. https://dot.ca.gov/programs/traffic-operations/mpr/pems-source
Chandra, S. R., & Al-Deek, H. (2009). Predictions of freeway traffic speeds and volumes using vector autoregressive models. Taylor and Francis, 13(2), 53-72. https://www.tandfonline.com/journals/gits20
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of gated recurrent neural networks on sequence modeling. Arxiv, https://doi.org/10.48550/arXiv.1412.3555
Guan, Z. (2023). Real time object recognition based on yolo model. Theoretical and Natural Science, 137-143. https://doi.org/10.54254/2753-8818/28/20230450
Haghshenas, S. S., Astarita, V., Guido, G., Seraji, M. H. M. S., Gonzalez, P. A. A., Haghdadi, A., & Haghshenas, S. S. (2023). Assessment of machine learning techniques and traffic flow: Aqualitative and quantitative analysis. Semantic Scholar, 3, 119-129. https://doi.org/10.47852/bonviewjcce32021062
Huang, Z., Zhang, Z., Li, Y., & Zhao, D. (2024). Short-term traffic flow prediction: A method of MEA-LSTM model based on chaotic characteristics analysis. Journal of Sustainable Built Environment, 1(1), https://doi.org/10.70731/yk3fpz22
Johansson, U., Boström, H., Löfström, T., & Linusson, H. (2014). Regression conformal prediction with random forests. Springer Nature, 97, 55-176. http://dx.doi.org/10.1007/s10994-014-5453-0
Karim, A. A., & Nower, N. (2024). Probabilistic spatio-temporal graph convolutional network for traffic forecasting. Springer Nature Link, 54, 7070–7085.
Knol, D., Leeuw, F., Meirink, J. F., & Krzhizhanovskaya, V. (2021 Jun 09). Deep learning for solar irradiance nowcasting: A comparison of a recurrent neural network and two traditional methods. Computational Science – ICCS 2021 Conference paper. 12746, (pp. 309-322). Springer Nature Link.
Kumar, S., & Vanajakshi, L. (2015). Short-term traffic flow prediction using seasonal ARIMA model with limited input data. Springer Nature link, https://link.springer.com/article/10.1007/s12544-015-0170-8
Li, S., Chang, F., Liu, C., & Li, N. (2020). Vehicle counting and traffic flow parameter estimation for dense traffic scenes. IET Research, 14, 1517-1523. https://doi.org/10.1049/iet-its.2019.0521
Li, Y., Chai, S., Ma, Z., & Wang, G. (2021). A hybrid deep learning framework for long-term traffic flow prediction. IEEE, 9, 11264-11271. https://doi.org/10.1109/access.2021.3050836
Ma, C., Sun, K., Chang, L., & Qu, Z. (2023). Enhanced information graph recursive network for traffic forecasting. Electronics, 12(11), 2519, 2519.https://doi.org/10.3390/electronics12112519
Ma, Q., Huang, G. H., & Ullah, S. (2020). A multi-parameter chaotic fusion approach for traffic flow forecasting. IEEE Xplore, 8, 222774-222781. https://doi.org/10.1109/access.2020.3043777
Manoel, C., Jeong, Y. , Jeong, M., & Han, L. (2009). Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions. Sciencedirct, 36(3), 6164-6173. https://doi.org/10.1016/j.eswa.2008.07.069
Ren, C., Chai, C., Yin, C., Ji, H., Cheng, X., Gao, G., & Zhang, H. (2021). Short-term traffic flow prediction: A method of combined deep learnings. Journal of Advanced Transportation, 2021(1), 9928073. https://doi.org/10.1155/2021/9928073
Shigemi, R., Ando, H., Wada, K., & Mukai, R. (2023). Predicting traffic breakdown on expressways using linear combination of vehicle detector data. Nonlinear Theory and Its Applications, IEICE, 14(2), 416-427. https://doi.org/10.1587/nolta.14.416
Singh, P. (2019). Wading through Graph Neural Networks. https://spraphul.github.io/blog/GCN
Tran, Q. H., Fang, Y., Chou, T., Hoang, T. V., Wang, C., Vu, V. T., Ho, T. L. H., Le, Q., & Chen M. (2022). Short-term traffic speed forecasting model for a parallel multi-lane arterial road using gps-monitored data based on deep learning approach. Sustainability, 14(10), 6351. Https://doi.org/10.3390/su14106351.
Turki, A. I., & Hasson, S. T. (2023). Study estimating hourly traffic flow using artificial neural network: A M25 motorway case. Samarra Journal of Pure and Applied Science, 5(1), 47-59. https://doi.org/10.54153/sjpas.2023.v5i1.448
Vaikunth, M., Dejey, D., Vishaal, C., & Balamurali, S. (2024). Optimizing helmet detection with hybrid yolo pipelines: A detailed analysis. Big Data, IOT and Blockchain Trends 2025, 83-93. https://doi.org/10.5121/csit.2024.142406
Viola, P., & Jones, M. (2001, December). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001 (Vol. 1, pp. I-I). IEEE. https://ieeexplore.ieee.org/document/990517
Wang, S., Zhang, X., Li, F., Yu, P. S., & Huang, Z. (2018). Efficient traffic estimation with multi-sourced data by parallel coupled hidden markov model. IEEE, 20(8), 3010-3023. Https://ieeexplore.ieee.org/Xplore/home.jsp
Yang, D., Chen, K., Yang, M., & Zhao, X. (2019). Urban rail transit passenger flow forecast based on LSTM with enhanced long-term features. SemanticScholar, 13(10), 1475-1482. https://doi.org/10.1049%2Fiet-its.2018.5511
Yang, P., Chen, Z., Su, G., & Wang, B. (2024). Enhancing traffic flow monitoring with machine learning integration on cloud data warehousing. ResearchGate, 67, 1-7. Https://doi.org/10.54254/2755-2721/67/2024ma0058
Yu, B., Yin H., & Zhu, Z. (2017). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. ArXiv, 3634-3640. https://doi.org/10.24963/ijcai.2018/505
Zhao, Z., Chen, W., Wu, X., Chen, P. C., & Liu, J. (2017). LSTM network: A deep learning approach for short‐term traffic forecast. IET intelligent transport systems, 11(2), 68-75. http://dx.doi.org/10.1049/iet-its.2016.0208
Zhao, L., Song, Y., Zhang, C., Liu, Y., Wang, P., & Lin, T. (2019 Aug 22). T-GCN: A Temporal Graph Convolutional Network for Trafic Prediction. IEEE Transactions on Intelligent Transportation Systems (pp. 3848-3858. https://ieeexplore.ieee.org/document/8809901).
Zhu, H., Xie, Y., He, W., Sun, C., Zhu, K., Zhou, G., & Ma, N. (2020). A novel traffic flow forecasting method based on RNN-GCN and BRB. Journal of Advanced Transportation, 2020(1), 7586154. http://dx.doi.org/10.1155/2020/7586154