journal article·2022-11-19Open access

Identifying Spatial–Temporal Characteristics and Significant Factors of Bus Bunching Based on an eGA and DT Model

Min Yan, Binglei Xie, Gangyan Xu

Applied Sciences· Volume 12· Issue 22

Abstract

Bus bunching is a common phenomenon caused by irregular bus headway, which increases the passenger waiting time, makes the passenger capacity uneven, and severely reduces the reliability of bus service. This paper clarified the process of bus bunching formation, analyzed the variation characteristics of bus bunching in a single day, in different types of periods, and at different bus stops, then concluded twelve potential factors. A hybrid model integrating a genetic algorithm with elitist preservation strategy (eGA) and decision tree (DT) was proposed. The eGA part constructs the model framework and transforms the factor identification into a problem of selecting the fittest individual from the population, while the DT part evaluates the fitness. Model verification and comparison were conducted based on real automatic vehicle location (AVL) data in Shenzhen, China. The results showed that the proposed eGA–DT model outperformed other frequently used single DT and extra tree (ET) models with at least a 20% reduction in MAE under different bus routes, periods, and bus stops. Six factors, including the sequence of the bus stop, the headway and dwell time at the previous bus stop, the travel time between bus stops, etc., were identified to have a significant effect on bus bunching, which is of great value for feature selection to improve the accuracy and efficiency of bus bunching prediction and real-time bus dispatching.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Transportation Planning and Optimization · Traffic Prediction and Management Techniques · Urban Transport and Accessibility

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Architecture, Harbin Institute of Technology, Shenzhen 518055, China

Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong SAR, China

Funding

National Natural Science Foundation of China · The Science and Technology Innovation Committee of Shenzhen

References (34)

Show source-provided references
1. Newell, G.F., and Potts, R.B. (, January January). Maintaining a Bus Schedule. Proceedings of the 2nd Australian Road Research Board (ARRB) Conference, Melbourne, Australia.
2. Feng, W., and Figliozzi, M. (2011, January 10–13). Identifying Spatial-Temporal Attributes of Bus Bunching through AVL/APC Data. Proceedings of the Institute of Transportation Engineers (ITE) Western States Annual Meeting, Anchorage, Alaska.
3. Du, B., and Dublanche, P.-A. (2018, January 11–13). Bus Bunching Identification Using Smart Card Data. Proceedings of the 2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS), Singapore.10.1109/PADSW.2018.8644611 ↗
4. Moreira-Matias, L., Gama, J., Mendes-Moreira, J., and Freire de Sousa, J. (2014). An Incremental Probabilistic Model to Predict Bus Bunching in Real-Time. Advances in Intelligent Data Analysis XIII, Springer. Lecture Notes in Computer Science.10.1007/978-3-319-12571-8_20 ↗
5. Ryus, P., Danaher, A., Walker, M., Nichols, F., Carter, B., Ellis, E., Cherrington, L., and Bruzzone, A. (2013). Transit Capacity and Quality of Service Manual, The National Academies Press. [3rd ed.].
6. Bus bunching along a corridor served by two lines10.1016/j.trc.2016.04.015 ↗
7. Have they bunched yet? An exploratory study of the impacts of bus bunching on dwell and running times10.1007/s12469-016-0126-y ↗
8. Modelling bus bunching under variable transit demand using cellular automata10.1007/s12469-019-00203-2 ↗
9. Evaluation of urban bus service reliability on variable time horizons using a hybrid deep learning method10.1016/j.ress.2021.108090 ↗
10. Bus-arrival time prediction using bus network data model and time periods10.1016/j.future.2018.04.077 ↗
11. Using survival models to estimate bus travel times and associated uncertainties10.1016/j.trc.2016.11.013 ↗
12. Modeling bus passenger boarding/alighting times: A stochastic approach
13. Estimating the route-level passenger demand profile from bus dwell times10.1016/j.trc.2021.103273 ↗
14. Evaluation of roadway spatial-temporal travel speed estimation using mapped low-frequency AVL probe data10.1016/j.measurement.2020.108150 ↗
15. Liu, Y., Qing, R., Zhao, Y., and Liao, Z. (2022). Road Intersection Recognition via Combining Classification Model and Clustering Algorithm Based on GPS Data. ISPRS Int. J. Geo-Inf., 11.10.3390/ijgi11090487 ↗
16. Identifying spatio-temporal patterns of bus bunching in urban networks10.1080/15472450.2020.1722949 ↗
17. Iliopoulou, C., Milioti, C., Vlahogianni, E., Kepaptsoglou, K., and Sanchez-Medina, J. (2018, January 4–7). The Bus Bunching Problem: Empirical Findings from Spatial Analytics. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA.10.1109/ITSC.2018.8569760 ↗
18. Feng, W., and Figliozzi, M. (2011, January 14–17). Empirical Findings of Bus Bunching Distributions and Attributes Using Archived AVL/APC Bus Data. Proceedings of the 11th International Conference of Chinese Transportation Professionals 2011 (ICCTP 2011), Nanjing, China.10.1061/41186(421)427 ↗
19. Prediction of Trends in Bus Travel Time Using Spatial Patterns10.1016/j.trpro.2020.08.128 ↗
20. A Model of Bus Bunching under Reliability-based Passenger Arrival Patterns10.1016/j.trpro.2015.06.015 ↗
21. Finding Causes of Irregular Headways Integrating Data Mining and AHP10.3390/ijgi4042604 ↗
22. Traffic Congestion Prediction using Decision Tree, Logistic Regression and Neural Networks
23. Bus travel time prediction: A log-normal auto-regressive (AR) modelling approach
24. Yuan, Y., Zhang, W., Yang, X., Liu, Y., Liu, Z., and Wang, W. (2021). Traffic state classification and prediction based on trajectory data. J. Intell. Transp. Syst., 1–15.10.1080/15472450.2021.1955210 ↗
25. Using Automatic Vehicle Location Data to Model and Identify Determinants of Bus Bunching10.1016/j.trpro.2017.05.170 ↗
26. Modeling bus bunching using massive location and fare collection data10.1080/15472450.2018.1494596 ↗
27. Factors affecting bus bunching at the stop level: A geographically weighted regression approach10.1016/j.ijtst.2020.04.001 ↗
28. Iliopoulou, C., Vlahogianni, E., and Kepaptsoglou, K. (2020, January 20–23). Understanding the factors that affect the bus bunching events’ duration. Proceedings of the 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece.10.1109/ITSC45102.2020.9294357 ↗
29. Robust timetable optimization for bus lines subject to resource and regulatory constraints10.1016/j.tre.2019.05.016 ↗
30. Validating the coverage of bus schedules: A Machine Learning approach10.1016/j.ins.2014.09.005 ↗
31. A holding strategy to resist bus bunching with dynamic target headway10.1016/j.cie.2019.106237 ↗
32. Comparing bus holding methods with and without real-time predictions10.1016/j.trc.2017.07.012 ↗
33. Dynamic bus substitution strategy for bunching intervention10.1016/j.trb.2018.06.001 ↗
34. A predictive headway-based bus-holding strategy with dynamic control point selection: A cooperative game theory approach10.1016/j.trb.2019.05.001 ↗