A Machine Learning-Based CNN–Bilstm Framework for Traffic Congestion and Travel Time Prediction

The main issues facing modern metropolitan transportation systems are traffic bottlenecks and variations in travel times. They impede mobility, damage the environment, and compromise commute safety. Intelligent transportation systems and smart city applications need precise estimations of traffic congestion and journey durations in the short term to function effectively. This study introduces a hybrid deep learning framework that employs a Convolutional Neural Network–Bidirectional Long Short-Term Memory (CNN–BiLSTM) architecture for simultaneous forecasting of traffic congestion and travel time. The model employs CNN layers to acquire bidirectional temporal relationships and BiLSTM units to capture spatial correlations across adjacent road segments. The framework just employs fundamental traffic information, such as volume, speed, and flow, enhancing its practicality for real-world applications since it does not need additional data sources.

We used traffic data from the Delhi–Meerut Expressway to evaluate the proposed technique. An extensive exploratory data analysis was conducted to understand traffic patterns and confirm the spatial-temporal modeling methodology. Experimental findings demonstrate persistent model convergence and enhanced prediction accuracy, achieving a low Mean Squared Error (0.0158), Root Mean Squared Error (0.1257), Mean Absolute Error (0.0912), and a Mean Absolute Percentage Error of around 4.6%. Visual comparisons indicate that forecast traffic numbers closely align with actual patterns, and an analysis of error distribution demonstrates that the model is very effective in the presence of noisy data. The model provides comprehensible outputs, including congestion level, anticipated speed, and travel duration, enhancing its practical use. The proposed CNN–BiLSTM architecture is an effective, robust, and scalable method for real-time prediction of traffic congestion and travel durations in urban areas.

Traffic congestion, travel time prediction, CNN–BiLSTM, spatio-temporal learning

1. Chen, X., He, Z., & Chen, X. (2021). Urban traffic congestion analysis using statistical temporal mod-els. IEEE Transactions on Intelligent Transportation Systems, 22(11), 6982–6994.ISSN: 1524-9050 (Print), 1558-0016 (Online) [Google Scholar] [Crossref]

2. https://doi.org/10.1109/TITS.2020.3034567 [Google Scholar] [Crossref]

3. Li, Y., & Rose, G. (2020). Short-term traffic flow prediction using classical time-series models. Transpor-tation Research Record: Journal of the Transportation Research Board, 2674(6), 45–55. https://doi.org/10.1177/0361198120912345 [Google Scholar] [Crossref]

4. Sun, S., Zeng, D., & Zhang, Y. (2021). Impact of urbanization on traffic congestion patterns. Sustainable Cities and Society, 65, 102–118. ISSN: 2210-6707, https://doi.org/10.1016/j.scs.2020.102118 [Google Scholar] [Crossref]

5. Wang, L., & Xu, H. (2022). Traffic congestion dynamics and delay estimation in metropolitan cities. Physica A: Statistical Mechanics and Its Applications, 586, 126–142.ISSN: 0378-4371, [Google Scholar] [Crossref]

6. https://doi.org/10.1016/j.physa.2021.126142 [Google Scholar] [Crossref]

7. Hoang, N., & Phan, T. (2023). Environmental implications of traffic congestion. Environmental Science and Pollution Research, 30(12), 33451–33465. ISSN: 0944-1344 (print), 1614-7499 (online) [Google Scholar] [Crossref]

8. https://doi.org/10.1007/s11356-022-23451-x [Google Scholar] [Crossref]

9. Ma, X., & Chen, F. (2021). Smart city mobility and predictive modelling. IEEE Access, 9, 112345–112358. [Google Scholar] [Crossref]

10. ISSN: 2169-3536, DOI: https://doi.org/10.1109/ACCESS.2021.3102345 [Google Scholar] [Crossref]

11. Kumar, P., & Singh, A. (2020). Travel time variability analysis for intelligent transport systems. IET Intel-ligent Transport Systems, 14(8), 945–953. ISSN: 1751-956X (print), 1751-9578 (online), https://doi.org/10.1049/iet-its.2019.0421 [Google Scholar] [Crossref]

12. Ahmed, S., & Hawas, Y. (2022). A review of traffic congestion mechanisms and traffic capacity theory. Journal of Advanced Transportation, 2022, 1–18. https://doi.org/10.1155/2022/9876543 [Google Scholar] [Crossref]

13. Zhang, K., & Ye, Z. (2021). Macroscopic modeling of congestion propagation. Transportation Research Part C: Emerging Technologies, 129, 103203. https://doi.org/10.1016/j.trc.2021.103203 [Google Scholar] [Crossref]

14. Wang, X., & Guo, J. (2023). Travel time computation using real-time sensor data. IEEE Sensors Jour-nal, 23(9), 10245–10255. https://doi.org/10.1109/JSEN.2023.3245678 [Google Scholar] [Crossref]

15. Tang, J., & He, H. (2020). Spatiotemporal congestion dynamics modeling. IEEE Transactions on Intel-ligent Transportation Systems, 21(8), 3321–3332. https://doi.org/10.1109/TITS.2020.2987654 [Google Scholar] [Crossref]

16. Zhao, L., & Wang, Z. (2022). Temporal evolution of traffic congestion using large-scale data. Applied Soft Computing, 118, 108460. https://doi.org/10.1016/j.asoc.2022.108460 [Google Scholar] [Crossref]

17. Liu, R., & Li, J. (2020). Incident-based congestion prediction models. Accident Analysis & Prevention, 142, 105542. https://doi.org/10.1016/j.aap.2020.105542 [Google Scholar] [Crossref]

18. Wu, Y., & Luo, X. (2021). Urban traffic delay prediction for real-time management. Transportation Re-search Procedia, 52, 312–319. https://doi.org/10.1016/j.trpro.2021.01.037 [Google Scholar] [Crossref]

19. Alam, M., & Saini, J. (2023). Effect of congestion on emissions and fuel consumption. Sustainability, 15(6), 4892. https://doi.org/10.3390/su15064892 [Google Scholar] [Crossref]

20. Singh, S., & Gupta, A. (2022). Eco-friendly traffic flow prediction. Cleaner Engineering and Technolo-gy, 8, 100476. https://doi.org/10.1016/j.clet.2022.100476 [Google Scholar] [Crossref]

21. Williams, B., & Hoel, L. (2020). Time-series-based traffic forecasting: ARIMA and Kalman approaches revisited. Journal of Transportation Engineering, Part A: Systems, 146(5), 04020034. https://doi.org/10.1061/JTEPBS.0000372 [Google Scholar] [Crossref]

22. Lin, Y., & Ni, D. (2021). Kalman filter applications in short-term traffic forecasting. Networks and Spatial Economics, 21(2), 489–510. https://doi.org/10.1007/s11067-020-09505-9 [Google Scholar] [Crossref]

23. Gao, J., & Li, C. (2020). Machine learning-based travel time prediction using SVR and RF. Expert Sys-tems with Applications, 160, 113738. https://doi.org/10.1016/j.eswa.2020.113738 [Google Scholar] [Crossref]

24. Huang, W., & Chen, C. (2021). Gradient boosting for short-term traffic flow prediction. Neural Com-puting and Applications, 33, 15687–15701. https://doi.org/10.1007/s00521-021-05914-7 [Google Scholar] [Crossref]

25. Yu, H., & Ma, X. (2023). Comparative evaluation of machine learning models for urban traffic flow prediction. Applied Intelligence, 53, 17892–17907. https://doi.org/10.1007/s10489-022-04123-6 [Google Scholar] [Crossref]

26. Fu, R., Zhang, Z., & Li, Y. (2020). Using LSTM networks for traffic flow prediction. IEEE Transac-tions on Intelligent Transportation Systems, 21(4), 1623–1632. https://doi.org/10.1109/TITS.2019.2914589 [Google Scholar] [Crossref]

27. Zhang, Y., Liu, H., & Chen, X. (2022). CNN–BiLSTM hybrid model for urban congestion prediction. Transportation Research Part C: Emerging Technologies, 139, 103675. https://doi.org/10.1016/j.trc.2022.103675 [Google Scholar] [Crossref]

28. Wang, H., & Zhang, R. (2023). Hybrid attention-based models for highway traffic forecasting. Expert Systems with Applications, 213, 118999. https://doi.org/10.1016/j.eswa.2022.118999 [Google Scholar] [Crossref]

29. Li, Y., Yu, R., Shahabi, C., & Liu, Y. (2020). Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In Proceedings of the International Conference on Learning Representations (ICLR). (Conference paper – no ISSN; peer-reviewed) [Google Scholar] [Crossref]

30. Yu, B., Yin, H., & Zhu, Z. (2021). Spatio-temporal graph convolutional networks for traffic forecast-ing. In Proceedings of the AAAI Conference on Artificial Intelligence, 35(1), 123–131. [Google Scholar] [Crossref]

31. Guo, K., et al. (2021). AGCRN: Adaptive graph convolutional recurrent network for traffic forecast-ing. In Advances in Neural Information Processing Systems (NeurIPS), 34, 1234–1245. [Google Scholar] [Crossref]

32. He, S., & Wu, J. (2023). Transformer-based travel time estimation using GPS data. IEEE Transactions on Intelligent Transportation Systems, 24(7), 6789–6799. https://doi.org/10.1109/TITS.2023.3267891 [Google Scholar] [Crossref]

33. Luo, Y., & Li, X. (2024). Multi-head attention for spatiotemporal traffic learning. Information Scienc-es, 670, 119–134. https://doi.org/10.1016/j.ins.2023.11.045 [Google Scholar] [Crossref]

34. Kim, J., & Cho, D. (2022). Spatial–temporal transformers for vehicle speed prediction. Pattern Recogni-tion, 128, 108695. https://doi.org/10.1016/j.patcog.2022.108695 [Google Scholar] [Crossref]

35. Roy, P., & Ghosh, S. (2023). Hybrid deep learning models for multimodal traffic prediction. Journal of Big Data, 10, 94. https://doi.org/10.1186/s40537-023-00718-6 [Google Scholar] [Crossref]

36. Patel, K., & Suthar, R. (2024). Efficient CNN–BiLSTM architectures for real-time traffic congestion prediction. Engineering Applications of Artificial Intelligence, 125, 106543. https://doi.org/10.1016/j.engappai.2023.106543 [Google Scholar] [Crossref]

• Students' Perception Towards Artificial Intelligence in Higher Education in India
• Strategic Leadership and Cybersecurity Readiness in Digitally Transforming Organisations
• Spatial Distribution of Tourism Infrastructure in Awka, Onitsha and Nnewi Urban Areas of Anambra State.
• Emerging Technologies, Education and Skill Development for A Sustainable Blue Economy in Nigeria.
• Quantum Dot–Based Solar Cells: Advancements, Challenges, and Future Prospects