Research methods for digitalization of transport systems using artificial intelligence
- Autores: Podberezkin A.A.1, Ostroukh A.V.1, Borzenkov A.M.1, Shmonin A.M.1, Pronin C.B.1
-
Afiliações:
- Moscow Automobile and Road Construction State Technical University
- Edição: Volume 15, Nº 3 (2025)
- Páginas: 141-166
- Seção: Articles
- ##submission.datePublished##: 25.11.2025
- URL: https://ogarev-online.ru/2328-1391/article/view/356726
- DOI: https://doi.org/10.12731/3033-5965-2025-15-3-396
- ID: 356726
Citar
Texto integral
Resumo
Background. There is a need to move from isolated “point” solutions to comprehensive digitalization of transport systems that integrates infrastructure-level pavement monitoring, operational traffic management, and strategic planning. To this end, it is reasonable to combine machine learning (for forecasting), genetic algorithms (for optimization), and multi-agent simulation (for robustness checking).
Purpose. To assess the effect of such integration using a set of metrics (delays, costs, risk, profit, service) and an integral objective function F.
Materials and methods. Infrastructure level: computer vision (YOLO), mAP ≈ 0.84; defect-generation forecasting (XGBoost), error ≤ 12%. Operational level: short-term traffic-intensity forecasts (LSTM/XGBoost, RMSE 8–10%) and traffic-signal phase optimization with a genetic algorithm. Strategic level: demand and tariff forecasting, optimization scenarios. The robustness of solutions was verified via multi-agent simulation; comparisons were made against baseline (“as-is”) scenarios.
Results. Total delays were reduced by 37%, overall logistics costs by 12%, and profitability increased by 10–11%; with a 20% demand increase, >90% of deliveries were completed within SLA. The integral function F improved by 22–24%. The plans demonstrated robustness and sensitivity to criterion weights.
Sobre autores
Aleksandr Podberezkin
Moscow Automobile and Road Construction State Technical University
Autor responsável pela correspondência
Email: a.podberezkin@gmail.com
Senior Lecturer of the Department of Automated Control Systems
Rússia, 64, Leningradsky pr., Moscow, 125319, Russian Federation
Andrey Ostroukh
Moscow Automobile and Road Construction State Technical University
Email: ostroukh@mail.ru
Doctor of Technical Sciences, Professor, Professor of the Department of Automated Control Systems
Rússia, 64, Leningradsky pr., Moscow, 125319, Russian Federation
Aleksandr Borzenkov
Moscow Automobile and Road Construction State Technical University
Email: borzenkov03h@mail.ru
Student of the Department of Automated Control Systems
Rússia, 64, Leningradsky pr., Moscow, 125319, Russian Federation
Artyom Shmonin
Moscow Automobile and Road Construction State Technical University
Email: shmoninam@mail.ru
Student of the Department of Automated Control Systems
Rússia, 64, Leningradsky pr., Moscow, 125319, Russian Federation
Cezar Pronin
Moscow Automobile and Road Construction State Technical University
Email: caesarpr12@gmail.com
Senior Lecturer of the Department of Automated Control Systems
Rússia, 64, Leningradsky pr., Moscow, 125319, Russian Federation
Bibliografia
- Ministry of Internal Affairs of the Russian Federation [MVD Rossii]. (n.d.). Analytical reviews of road safety status. Retrieved from https://нцбдд.мвд.рф/ресурсы/аналитические обзоры состояния безопасно (accessed: 20.07.2025).
- Rosstandart. (2017). GOST R 50597-2017. Roads and streets. Requirements for operational condition. Moscow: Standartinform. 21 pp.
- Ministry of Regional Development of the Russian Federation [Minregion Rossii]. (2012). SP 78.13330.2012. Roads. Updated version of SNiP 2.05.02-85. Moscow. 89 pp.
- Akopov, A. S. (2025). MBHGA: A matrix-based hybrid genetic algorithm for solving an agent-based model of controlled trade interactions. IEEE Access, 13, 26843–26863. https://doi.org/10.1109/ACCESS.2025.3539460. EDN: https://elibrary.ru/NPLKCJ
- Borzenkov, A. M., Ostroukh, A. V., Pronin, C. B., Podberezkin, A. A., & Kuftinova, N. G. (2024). Multi-criteria analysis of genetic algorithm applications in transportation logistics. In 2024 Intelligent Technologies and Electronic Devices in Vehicle and Road Transport Complex (TIRVED) (pp. 1–4). Moscow. https://doi.org/10.1109/TIRVED63561.2024.10769798
- Ceylan, H., & Bell, M. G. H. (2018). Traffic signal timing optimization based on genetic algorithm approach, including driver’s route choice. Transportation Research Part B: Methodological, 114, 25–41. https://doi.org/10.1016/j.trb.2018.05.009
- World Health Organization [WHO]. (2023). Global status report on road safety 2023. Geneva. 232 p. Retrieved from https://www.who.int/publications/i/item/9789241565684 (accessed: 05.07.2025).
- Hauer, E. (2004). The harm done by tests of significance. Accident Analysis & Prevention, 36(3), 495–500. https://doi.org/10.1016/S0001-4575(03)00036-8. Retrieved from https://www.sciencedirect.com/science/article/abs/pii/S0001457503000368 (accessed: 05.08.2025).
- Kiselev, S. A., Podberezkin, A. A., Borzenkov, A. M., Ostroukh, A. V., & Pronin, C. B. (2025). Dynamic pricing in air cargo: Machine learning and genetic algorithm-based optimization. В 2025 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF) (с. 1–5). St. Petersburg, Russian Federation. https://doi.org/10.1109/WECONF65186.2025.11017136
- Mansurova, M. et al. (2024). Multi-level intelligent control system for inter-vehicle communication between smart traffic lights with computer vision and autonomous electric vehicles. В 2024 International Symposium on Sensing and Instrumentation in 5G and IoT Era (ISSI) (с. 1–6). Lagoa, Portugal. https://doi.org/10.1109/ISSI63632.2024.10720507
- Ostroukh, A., Kuftinova, N., Borzenkov, A., Podberezkin, A., & Ostroukh, I. (2024). Research on using deep learning for transport demand prediction. В 2024 Intelligent Technologies and Electronic Devices in Vehicle and Road Transport Complex (TIRVED) (с. 1–5). Moscow. https://doi.org/10.1109/TIRVED63561.2024.10769599
- Puscar, F. M. (2017). Safety diagnosis of vehicle-bicycle interactions using computer vision systems: A case study in Vancouver, B.C. (Магистерская диссертация). University of British Columbia, Vancouver, BC, Canada. https://doi.org/10.14288/1.0343989. Retrieved from https://open.library.ubc.ca/soa/cIRcle/collections/ubctheses/24/items/1.0343989 (accessed: 06.08.2025).
- Radeev, N., & Vinogradova, K. (2025). Semi-automated framework for feature engineering in machine learning and data analysis. В 2025 IEEE 26th International Conference of Young Professionals in Electron Devices and Materials (EDM) (с. 1520–1525). Altai, Russian Federation. https://doi.org/10.1109/EDM65517.2025.11096892
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. В 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (с. 779–788). Las Vegas, NV, USA. https://doi.org/10.1109/CVPR.2016.91
- St-Aubin, P., Saunier, N., & Miranda-Moreno, L. (2017). Large-scale automated proactive road safety analysis using video data. University of British Columbia. https://doi.org/10.1016/j.trc.2015.04.007. Retrieved from https://www.researchgate.net/publication/275412773_Large-scale_automated_proactive_road_safety_analysis_using_video_data (accessed: 06.08.2025).
- Yan, S., Fu, Y., Zhang, W., Yang, W., Yu, R., & Zhang, F. (2023). Multi-target instance segmentation and tracking using YOLOv8 and BoT-SORT for video SAR. В 2023 5th International Conference on Electronic Engineering and Informatics (EEI) (с. 506–510). Wuhan, China. https://doi.org/10.1109/EEI59236.2023.10212903
- Zhang, Z., Zhu, H., Zhang, W., Cai, Z., Zhu, L., & Li, Z. (2023). Multi-objective optimization of traffic signal timing at typical junctions based on genetic algorithms. Computer Systems Science and Engineering, 47, 1901–1917. https://doi.org/10.32604/csse.2023.039395. EDN: https://elibrary.ru/FPUNQR
Arquivos suplementares
