ENGINEERING TRAFFIC FLOW STABILITY USING ENTROPY COMPLEXITY METRICS AND TOLL-BASED MIXED VEHICLE ANALYTICS
DOI:
https://doi.org/10.55766/sujst11027Keywords:
Traffic Forecasting, Permutation Entropy, Vehicle Classification, Indian Highways, Prediction Stability, Time Series Analysis, Toll DataAbstract
In developing countries, prediction of traffic flow in heterogeneous classes of vehicles is important in planning the infrastructure and management of congestion. Although many models exist, research assessing their temporal generalizability to disaggregated vehicle types remains limited. This paper evaluates forecasting efficiency and temporal complexity of vehicle-wise traffic flow using a 60-month toll dataset and 20-month projections. The forecasts were developed by applying machine learning and regression-based techniques to generate a number of models including Random Forests, CatBoost, XGBoost, Bayesian Ridge, Elastic Net, etc. Accuracy was measured via Mean Absolute Percentage Error (MAPE), Mean Absolute Deviation (MAD), Mean Squared Deviation (MSD) and permutation entropy (PE, m = 3, τ = 1) was used to assess dynamic complexity. Permutation entropy (PE) was calculated on every category to compare the complexity of observed and estimated traffic. The results indicate that categories such as CAR-JEEP-VAN and MONTHLY PASS VEHICLES exhibit increasing entropy in the projections, suggesting a greater unpredictability. In contrast, heavy vehicle categories such as TRUCK and MINI BUS-LCV show markedly reduced entropy, indicating over simplified patterns. The main conclusion is that vehicle-specific forecasting models provide a realistic yet accurate complexity while Entropy-based diagnostics provide a novel validity check, ensuring forecasts capture realistic dynamic complexity and supporting robust, class-specific traffic planning decisions.
References
Akhtar, M., & Moridpour, S. (2021). A review of traffic congestion prediction using artificial intelligence. Journal of Advanced Transportation, 2021(1), 8878011. https://doi.org/10.1155/2021/8878011
Basu, S., & Saha, P. (2022). Evaluation of risk factors for road accidents under mixed traffic: Case study on Indian highways. IATSS Research, 46(4), 559-573. https://doi.org/10.1016/j.iatssr.2022.09.004
Bayer, S. B., & Flügel, S. (2025). Introduction vs. price change of road toll - a panel data analysis of revealed preferences. Research in Transportation Economics, 112, 101592. https://doi.org/10.1016/j.retrec.2025.101592
Gomes, B., Coelho, J., & Aidos, H. (2023). A survey on traffic flow prediction and classification. Intelligent Systems with Applications, 20, 200268. https://doi.org/10.1016/j.iswa.2023.200268
Hammoumi, L., Farah, S., Benayad, M., Maanan, M., & Rhinane, H. (2025). Leveraging machine learning to predict traffic jams: Case study of Casablanca, Morocco. Journal of Urban Management. https://doi.org/10.1016/j.jum.2025.02.004
Han, J., Wang, X., & Wang, G. (2022). Modeling the car-following behavior with consideration of driver, vehicle, and environment factors: A historical review. Sustainability, 14(13), 8179. https://doi.org/10.3390/su14138179
Kim, J., Kim, H., Kim, H. G., Lee, D., & Yoon, S. (2025). A comprehensive survey of deep learning for time series forecasting: Architectural diversity and open challenges. Artificial Intelligence Review, 58(7), 1-95. https://doi.org/10.1007/s10462-025-11223-9
Kokatnur, K. B., Kulkarni, S. S., Shamshuddin, K., Budihal, S. V., & Devika, S. (2024). Harnessing DSRC for intersection movement assist (IMA) in vehicle-to-vehicle communication. In Lecture Notes in Networks and Systems (Vol. 1111, pp. 25-34). Springer. https://doi.org/10.1007/978-981-97-6681-9_3
Kumar, S. S. M., Pandey, M., & Umamahesh, N. V. (2024). Predicting total upland sediment yield using regression and machine learning models for improved land management and water conservation. Journal of Hydroinformatics, 26(8), 2045-2058. https://doi.org/10.2166/hydro.2024.159
Lv, Z., & Shang, W. (2023). Impacts of intelligent transportation systems on energy conservation and emission reduction of transport systems: A comprehensive review. Green Technologies and Sustainability, 1(1), 100002. https://doi.org/10.1016/j.grets.2022.100002
Mihailovi´cmihailovi´c, D. T. (2025). Permutation entropy and its niche in hydrology: A review. Entropy, 27(6), 598. https://doi.org/10.3390/e27060598
Mystakidis, A., Koukaras, P., & Tjortjis, C. (2025). Advances in traffic congestion prediction: An overview of emerging techniques and methods. Smart Cities, 8(1), 25. https://doi.org/10.3390/smartcities8010025
Piadeh, F., Behzadian, K., & Alani, A. M. (2022). A critical review of real-time modelling of flood forecasting in urban drainage systems. Journal of Hydrology, 607, 127476. https://doi.org/10.1016/j.jhydrol.2022.127476
Pisarchik, A. N., & Hramov, A. E. (2023). Coherence resonance in neural networks: Theory and experiments. Physics Reports, 1000, 1-57. https://doi.org/10.1016/j.physrep.2022.11.004
Rasulmukhamedov, M., Tashmetov, T., & Tashmetov, K. (2024). Forecasting traffic flow using machine learning algorithms. Engineering Proceedings, 70(1), 14. https://doi.org/10.3390/engproc2024070014
Sayed, S. A., Abdel-Hamid, Y., & Hefny, H. A. (2023). Artificial intelligence-based traffic flow prediction: A comprehensive review. Journal of Electrical Systems and Information Technology, 10(1), 1-42. https://doi.org/10.1186/s43067-023-00081-6
Song, X., You, H., Zhou, S., & Xie, W. (2020). Traffic sign recognition with binarized multi-scale neural networks. In Proceedings of the 2020 35th Youth Academic Annual Conference of Chinese Association of Automation (YAC 2020) (pp. 116-121). IEEE. https://doi.org/10.1109/YAC51587.2020.9337571
Terven, J., Cordova-Esparza, D. M., Romero-González, J. A., Ramírez-Pedraza, A., & Chávez-Urbiola, E. A. (2025). A comprehensive survey of loss functions and metrics in deep learning. Artificial Intelligence Review, 58(7), 1-172. https://doi.org/10.1007/s10462-025-11198-7
Tyagi, A. K., & Aswathy, S. U. (2021). Autonomous intelligent vehicles (AIV): Research statements, open issues, challenges and road for future. International Journal of Intelligent Networks, 2, 83-102. https://doi.org/10.1016/j.ijin.2021.07.002
Willis, M. D., Harris, L., Campbell, E. J., Chaskes, M., Sawyer, E., Harleman, M., Ritz, B., Hill, E. L., & Hystad, P. (2024). A population-based cohort study of electronic tolling, traffic congestion, and adverse birth outcomes. Environment International, 183, 108355. https://doi.org/10.1016/j.envint.2023.108355
