Adaptive Time-Based Clustering for Optimizing Bus Fleet Management: A Case Study on İzmir’s Public Transportation System

Abstract

This study introduces an adaptive time-based clustering strategy to optimize bus fleet requirements in public transportation systems by leveraging passenger boarding data from İzmir's network. Addressing key challenges in scheduling and fleet sizing, the proposed method uses the K-Means clustering algorithm to segment boarding densities into optimally determined time intervals specific to each bus line and direction. By adapting the number and boundaries of time intervals to actual demand patterns across weekdays and weekends, the model offers a more responsive and efficient allocation of fleet resources. The results demonstrate that the adaptive clustering approach significantly outperforms the conventional fixed-interval strategy, reducing both maximum and average bus requirements while maintaining service quality. This improvement is especially notable for high-demand or highly variable lines, where resource flexibility is critical. While the study shows promising results, it also acknowledges limitations such as the exclusion of passenger waiting times and the diversity of the fleet composition. Future research may include integrating alternative clustering algorithms, incorporating alighting data, and developing multi-criteria operational planning models. These enhancements will further support the evolution of data-driven, adaptive planning tools for more efficient and sustainable urban transport systems.

Keywords

• Public Transportation Optimization
• Adaptive Clustering
• Frequency setting
• Bus Fleet Management

References

1. Aditi, A. D., Dureja, A., Abrol, S., & Dureja, A. (2020). Prediction of ticket prices for public transport using linear regression and random forest regression methods: A practical approach using machine learning. In U. Batra, N. Roy, & B. Panda (Eds.), Data science and analytics (pp. 140–150). Springer. https://doi.org/10.1007/978-981-15-5827-6_12 google scholar
2. Aksoy, İ. C., & Alver, Y. (2024). Addressing electric transit network design frequency setting problem with dynamic transit assignment. Transportmetrica B: Transport Dynamics, 12(1), 2318566. https://doi.org/10.1080/21680566.2023.2318566 google scholar
3. Aksoy, İ. C., & Mutlu, M. M. (2024). Comparing the performance of metaheuristics on the transit network frequency setting problem. Journal of Intelligent Transportation Systems, 1–20. google scholar
4. Bagheri, K., Samany, N. N., Toomanian, A., Jelokhani‐Niaraki, M., & Hajibabai, L. (2024). A planar graph cluster‐routing approach for optimizing medical waste collection based on spatial constraint. Transactions in GIS. google scholar
5. Benli, A., & Akgün, İ. (2023). A multi-objective mathematical programming model for transit network design and frequency setting problem. Mathematics, 11(21), 4488. https://doi.org/10.3390/math11214488 google scholar
6. Bertsimas, D., Ng, Y. S., & Yan, J. (2020). Joint frequency-setting and pricing optimization on multimodal transit networks at scale. Transportation Science, 54(3), 839–853. https://doi.org/10.1287/trsc.2019.0939 google scholar
7. Branda, F., Marozzo, F., & Talia, D. (2020). Ticket sales prediction and dynamic pricing strategies in public transport. Big Data and Cognitive Computing, 4(4), 36. https://doi.org/10.3390/bdcc4040036 google scholar
8. Carrel, A., Lau, P. S., Mishalani, R. G., Sengupta, R., & Walker, J. L. (2015). Quantifying transit travel experiences from the users’ perspective with high-resolution smartphone and vehicle location data: Methodologies, validation, and example analyses. Transportation Research Part C: Emerging Technologies, 58, 224–239. google scholar

9. Ceder, A. (2007). Public transit planning and operation: Theory, modeling and practice. Elsevier, Butterworth-Heinemann. google scholar
10. Charris, E. L. S., Montoya-Torres, J. R., & Guerrero-Rueda, W. (2019). A decision support system for technician routing with time windows: A case study of a Colombian public utility company. Academia Revista Latinoamericana de Administración, 32(2), 138–158. google scholar
11. Chen, Y., & Shan, T. (2021). Research on flexible public transportation planning based on node importance clustering. In CICTP 2021 (pp. 1800–1807). google scholar
12. dell’Olio, L., Ibeas, A., de Oña, J., & de Oña, R. (2018). Chapter 9 – Data mining approaches. In L. dell’Olio, A. Ibeas, J. de Oña, & R. de Oña (Eds.), Public transportation quality of service (pp. 155–179). Elsevier. http://dx.doi.org/10.1016/B978-0-08-102080-7.00009-4 google scholar
13. Gadepalli, R., Bansal, P., Tiwari, G., & Bolia, N. (2024). A tactical planning framework to integrate paratransit with formal public transport systems. Transportation Research Part D: Transport and Environment, 136, 104438. google scholar
14. Garrido, C., de Oña, R., & de Oña, J. (2014). Neural networks for analyzing service quality in public transportation. Expert Systems with Applications, 41, 6830–6838. http://dx.doi.org/10.1016/j.eswa.2014.04.045 google scholar
15. Gkiotsalitis, K., Schmidt, M., & van der Hurk, E. (2022). Subline frequency setting for autonomous minibusses under demand uncertainty. Transportation Research Part C: Emerging Technologies, 135, 103492. google scholar
16. Ibarra-Rojas, O. J., Delgado, F., Giesen, R., & Muñoz, J. C. (2015). Planning, operation, and control of bus transport systems: A literature review. Transportation Research Part B: Methodological, 77, 38–75. google scholar
17. Ibarra-Rojas, O. J., Muñoz, J. C., Giesen, R., & Knapp, P. (2019). Integrating frequency setting, timetabling, and route assignment to synchronize transit lines. Journal of Advanced Transportation, 2019(1), 9408595. google scholar
18. Jara-Díaz, S., Fielbaum, A., & Gschwender, A. (2017). Optimal fleet size, frequencies and vehicle capacities considering peak and off-peak periods in public transport. Transportation Research Part A: Policy and Practice, 106, 65–74. google scholar
19. Jing, D., Yao, E., Chen, R., & Sun, X. (2023). Optimal design method of public transit network considering transfer efficiency. IET Intelligent Transport Systems, 17(6), 1118–1136. google scholar
20. Kim, M., Kho, S. Y., & Kim, D. K. (2019). A transit route network design problem considering equity. Sustainability, 11(13), 3527. google scholar
21. Lee, I., Cho, S. H., Kim, K., Kho, S. Y., & Kim, D. K. (2022). Travel pattern-based bus trip origin-destination estimation using smart card data. PLOS ONE, 17(6), e0270346. google scholar
22. Ma, X., Wu, Y. J., Wang, Y., Chen, F., & Liu, J. (2013). Mining smart card data for transit riders’ travel patterns. Transportation Research Part C: Emerging Technologies, 36, 1–12. google scholar
23. Mayaud, J. R., Tran, M., & Nuttall, R. (2019). An urban data framework for assessing equity in cities: Comparing accessibility to healthcare facilities in Cascadia. Computers, Environment and Urban Systems, 78, 101401. https://doi.org/10.1016/j.compenvurbsys.2019. 101401 google scholar
24. Mete, S., Çelik, E., & Gül, M. (2022). Predicting the time of bus arrival for public transportation by time series models. Journal of Transportation and Logistics, 7(2), 541–555. google scholar
25. Mirza, A. M., & Jain, R. K. (2025). Review of public transportation integration and modeling strategies: Toward seamless urban mobility. Multidisciplinary Reviews, 8(1), 2025018–2025018. google scholar
26. Mutlu, M. M., Aksoy, İ. C., & Alver, Y. (2021). COVID-19 transmission risk minimization at public transportation stops using Differential Evolution algorithm. [Manuscript submitted for publication]. google scholar
27. Mutlu, M. M., Aksoy, İ. C., & Alver, Y. (2022). Transit frequency optimization in bi-modal networks using differential evolution algorithm. Teknik Dergi, 33(5), 12601–12616. google scholar
28. Oliveira, J. L. A., Aquino, A. L., Pinheiro, R. G., & Nogueira, B. (2024). Optimizing public transport system using biased random-key genetic algorithm. Applied Soft Computing, 158, 111578. google scholar
29. Pei, J., Zhong, K., Li, J., & Yu, Z. (2022). PAC: Partial area clustering for re-adjusting the layout of traffic stations in city’s public transport. IEEE Transactions on Intelligent Transportation Systems, 24(1), 1251–1260. google scholar
30. Pelletier, M. P., Trépanier, M., & Morency, C. (2011). Smart card data use in public transit: A literature review. Transportation Research Part C: Emerging Technologies, 19(4), 557–568. google scholar
31. Pojani, D., & Stead, D. (2015). Sustainable urban transport in the developing world: Beyond megacities. Sustainability, 7(6), 7784–7805. google scholar
32. Purdy, M., & Daugherty, P. (2017). How AI boosts industry profits and innovation. Accenture Ltd. google scholar
33. Shalit, N., Fire, M., & Ben-Elia, E. (2020). Imputation of missing boarding stop information in smart card data with machine learning methods. In Intelligent Data Engineering and Automated Learning – IDEAL 2020 (pp. 17–27). https://doi.org/10.1007/978-3-030-62362-3_3 google scholar
34. Sosnowska, J., & Skibski, O. (2018). Path evaluation and centralities in weighted graphs—An axiomatic approach. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (pp. 3856–3862). google scholar
35. Tian, Q., Wang, D. Z., & Lin, Y. H. (2021). Service operation design in a transit network with congested common lines. Transportation Research Part B: Methodological, 144, 81–102. google scholar
36. Tran, L., Mun, M., Lim, M., Yamato, J., Huh, N., & Shahabi, C. (2020). DeepTRANS: A deep learning system for public bus travel time estimation using traffic forecasting. Proceedings of the VLDB Endowment, 13, 2957–2960. https://doi.org/10.14778/3415478.3415518 google scholar
37. UITP Asia Pacific Centre for Transport Excellence (CTE). (2020). Artificial intelligence in mass public transport: Executive summary. https:// cms.uitp.org/wp/wp-content/uploads/2020/08/UITP-AP-CTE-AI-in-PT-Executive-Summary-Dec-2018_0.pdf google scholar
38. Vlachopanagiotis, T., Grizos, K., Georgiadis, G., & Politis, I. (2021). Public transportation network design and frequency setting: Pareto optimality through alternating-objective genetic algorithms. Future Transportation, 1(2), 248–267. google scholar
39. Wei, M., Liu, T., Sun, B., & Jing, B. (2020). Optimal integrated model for feeder transit route design and frequency‐setting problem with stop selection. Journal of Advanced Transportation, 2020(1), 6517248. google scholar
40. Xie, Y., Guo, Y., Zhou, T., Mi, Z., Yang, Y., Sadoun, B., & Obaidat, M. S. (2020). A strategy to alleviate rush hour traffics in urban areas based on school-trip commute information. IEEE Systems Journal, 15(2), 2630–2641. google scholar
41. Yuan, Y., Shao, C., Cao, Z., He, Z., Zhu, C., Wang, Y., & Jang, V. (2020). Bus dynamic travel time prediction: Using a deep feature extraction framework based on RNN and DNN. Electronics, 9(11), 1876. https://doi.org/10.3390/electronics9111876 google scholar