Video-Based Comparative Modelling of Bus Dwell Time Using Parametric and Machine Learning Methods

Öz

This study models bus dwell time and compares different modelling techniques to identify key operational and passenger-related factors affecting it. Using manually collected stop-level data from İzmir, Türkiye, the analysis examined four main explanatory factors, namely, total boardings, in-vehicle crowding level, number of doors opened, and passenger complexity ratio. After data cleaning and outlier screening, the final modelling dataset included 381 observations. Parametric models, including Multiple Linear Regression (MLR), Elastic Net Regression (ENR), and Polynomial Regression (PR), were compared with non-parametric machine learning models, including k-Nearest Neighbors (KNN), Random Forest (RF), and XGBoost. Model performance was evaluated using R2, adjusted R2, Mean Squared Error, Mean Absolute Error, and Root Mean Squared Error. Among the parametric models, ENR provided the strongest performance, with an adjusted R2 of 71.4%. The ensemble-based models performed best overall, with XGBoost achieving the highest adjusted R2 of 77.5%, followed closely by RF. SHAP analysis confirmed that total boardings was the dominant predictor, followed by the number of doors opened, passenger complexity ratio, and high in-vehicle crowding. The TCQSM-style benchmark comparison showed that locally calibrated and data-driven models provided more accurate dwell-time estimates than externally parameterized service-time values. The findings show that video-based stop-level observations can support both interpretable and prediction-oriented bus dwell-time modelling.

Anahtar Kelimeler

• Bus dwell time
• public transportation modeling
• parametric models
• non-parametric models
• machine learning

Kaynakça

1. Kwesiga, D.K., Guin, A., Hunter, M., Analysis of bus dwell times from automated passenger count data and the impact of dwell-time variability on the performance of transit signal priority. Public Transport, 18, 311–333, 2026.
2. Milkovits, M.N., Modeling the Factors Affecting Bus Stop Dwell Time. Transportation Research Record: Journal of the Transportation Research Board, 2072, 125–130, 2008.
3. Kraft, W.H., Bergen, T.F., Evaluation of passenger service times for street transit systems. Transp. Res. Rec., 505, 1974.
4. Levinson, H.S., Analyzing Transit Travel Time Performance. Transp. Res. Rec., 915, 1–6, 1983.
5. Guenthner, R.P., Sinha, K.C., Modeling bus delays due to passenger boardings and alightings. Transp. Res. Rec., 915, 7–13, 1983.
6. Guenthner, R.P., Hamat, K., Transit Dwell Time Under Complex Fare Structure. J. Transp. Eng., 114, 367–379, 1988.
7. Lin, T., Wilson, N.H.M., Dwell time relationships for light rail systems. Transp. Res. Rec., 1361, 287–295, 1992.
8. Cats, O., West, J., Eliasson, J., A dynamic stochastic model for evaluating congestion and crowding effects in transit systems. Transportation Research Part B: Methodological, 89, 43–57, 2016.

9. Dueker, K., Kimpel, T., Strathman, J., Callas, S., Determinants of Bus Dwell Time. J. Public Trans., 7, 21–40, 2004.
10. Rajbhandari, R., Chien, S.I., Daniel, J.R., Estimation of Bus Dwell Times with Automatic Passenger Counter Information. Transportation Research Record: Journal of the Transportation Research Board, 1841, 120–127, 2003.
11. Tirachini, A., Bus dwell time: the effect of different fare collection systems, bus floor level and age of passengers. Transportmetrica A: Transport Science, 9, 28–49, 2013.
12. Khoo, H.L., Statistical modeling of bus dwell time at stops. Journal of the Eastern Asia Society for Transportation Studies, 10, 1489–1500, 2013.
13. Yoon, G.-G., HWANG, J., KIM, H.-S., LEE, C., Analyzing Relationship between Weather and Variability of Travel Time of Bus, in: Proceedings of the Eastern Asia Society for Transportation Studies, 2013.
14. El-Geneidy, A., Vijayakumar, N., The Effects of Articulated Buses on Dwell and Running Times. J. Public Trans., 14, 63–86, 2011.
15. Rashidi, S., Ataeian, S., Ranjitkar, P., Estimating bus dwell time: A review of the literature. Transp. Rev., 43, 32–61, 2023.
16. Rashidi, S., Ranjitkar, P., Hadas, Y., Modeling Bus Dwell Time with Decision Tree-Based Methods. Transportation Research Record: Journal of the Transportation Research Board, 2418, 74–83, 2014.
17. Xin, J., Chen, S., Bus Dwell Time Prediction Based on KNN. Procedia Eng., 137, 283–288, 2016.
18. Ding, J., Yang, M., Cao, Y., Kong, S.L., Dwell Time Prediction of Bus Rapid Transit Using ARIMA-SVM Hybrid Model. Applied Mechanics and Materials, 587–589, 1993–1997, 2014.
19. Chen, M., Xiaobo, L., Using a Neural Network to Analyze the Impact of Passenger Activity on Bus Dwell Time and Travel Time. Journal of the Transportation Research Forum, 44, 131–141, 2005.
20. Aydin, M.M., Yildirim, M.S., Aydin, R., Arslan, Y., Effect of different passenger characteristics and bus types on boarding times at bus-stops. Journal of Engineering Research and Applied Science, 5, 499–509, 2016.
21. Aswini, P.B., Savithramma, R.M., Sumathi, R., Bus Dwell Time Forecasting using Machine Learning Models, in: 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI), IEEE, 2023, pp. 1156–1161.
22. Wang, C., Ye, Z., Wang, Y., Xu, Y., et al., Modeling Bus Dwell Time and Time Lost Serving Stop in China. J. Public Trans., 19, 55–77, 2016.
23. Sun, B., Yang, Y., Dong, L., Lu, H., et al., Analysis and Dynamic Prediction of Bus Dwell Time Under Rainfall Conditions. Promet - Traffic&Transportation, 37, 105–121, 2025.
24. Bhele, R., Devkota, B.P., Dwell Time Variability at Bus Bays at Six Lane Road of Araniko Highway: Impact of Passenger Attributes and Bus Variation. Transactions on Transport Sciences, 16, 50–59, 2025.
25. Moosavi, S.M.H., Ismail, A., Balali, A., Evaluating bus dwell time at key stops using automatic data collection systems. Institute of Transportation Engineers. ITE Journal, 87, 45–49, 2017.
26. Özuysal, M., Çalışkanelli, S.P., Tanyel, S., A discussion on the dwell time values at bus stops. Pamukkale University Journal of Engineering Sciences, 22, 460–467, 2016.
27. Zou, H., Hastie, T., Regularization and Variable Selection Via the Elastic Net. J. R. Stat. Soc. Series B Stat. Methodol., 67, 301–320, 2005.
28. Cover, T., Hart, P., Nearest neighbor pattern classification. IEEE Trans. Inf. Theory, 13, 21–27, 1967.
29. Breiman, L., Random Forests. Mach. Learn., 45, 5–32, 2001.
30. Chen, T., Guestrin, C., XGBoost: A scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, New York, NY, USA 2016, pp. 785–794.
31. National Academies of Sciences Engineering and Medicine, Transit Capacity and Quality of Service Manual, Third Edition, The National Academies Press, Washington, D.C. 2013.