Exploring the Determinants of Pedestrian Crash Severity Using an AutoML Approach
Publication: International Conference on Transportation and Development 2024
ABSTRACT
This study investigates pedestrian crash severity through automated machine learning (AutoML), offering a streamlined and accessible method for analyzing critical factors. Utilizing a detailed dataset from Utah spanning 2010−2021, the research employs AutoML to assess the effects of various explanatory variables on crash outcomes. The study incorporates SHAP (SHapley Additive exPlanations) to interpret the contributions of individual features in the predictive model, enhancing the understanding of influential factors such as lighting conditions, road type, and weather on pedestrian crash severity. Emphasizing the efficiency and democratization of data-driven methodologies, the paper discusses the benefits of using AutoML in traffic safety analysis. This integration of AutoML with SHAP analysis not only bolsters predictive accuracy but also improves interpretability, offering critical insights into effective pedestrian safety measures. The findings highlight the potential of this approach in advancing the analysis of pedestrian crash severity.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
REFERENCES
Al-Mistarehi, B. W., Alomari, A. H., Imam, R., and Mashaqba, M. (2022). Using Machine Learning Models to Forecast Severity Level of Traffic Crashes by R Studio and ArcGIS. Frontiers in Built Environment, 8, 860805. https://doi.org/10.3389/fbuil.2022.860805.
Angarita-Zapata, J. S., Maestre-Gongora, G., and Calderín, J. F. (2021). A bibliometric analysis and benchmark of machine learning and automl in crash severity prediction: The case study of three colombian cities. Sensors, 21(24). https://doi.org/10.3390/s21248401.
Batista, G. E. A. P. A., Bazzan, A. L. C., and Monard, M. C. (2003). Balancing Training Data for Automated Annotation of Keywords: a Case Study. In Proceedings of the Second Brazilian Workshop on Bioinformatics, January.
Effati, M., and Vahedi Saheli, M. (2022). Examining the influence of rural land uses and accessibility-related factors to estimate pedestrian safety: The use of GIS and machine learning techniques. International Journal of Transportation Science and Technology, 11(1), 144–157. https://doi.org/10.1016/j.ijtst.2021.03.005.
Ferenchak, N. N., Gutierrez, R. E., and Singleton, P. A. (2022). Shedding light on the pedestrian safety crisis: An analysis across the injury severity spectrum by lighting condition. Traffic Injury Prevention, 23(7). https://doi.org/10.1080/15389588.2022.2100362.
Goswamy, A., Abdel-Aty, M., and Islam, Z. (2023). Factors affecting injury severity at pedestrian crossing locations with Rectangular RAPID Flashing Beacons (RRFB) using XGBoost and random parameters discrete outcome models. Accident Analysis & Prevention, 181, 106937. https://doi.org/10.1016/J.AAP.2022.106937.
Harris, L., Ahmad, N., Khattak, A., and Chakraborty, S. (2023). Exploring the Effect of Visibility Factors on Vehicle–Pedestrian Crash Injury Severity. Https://Doi.Org/10.1177/03611981231164070, 036119812311640. https://doi.org/10.1177/03611981231164070.
Infante, P., et al. (2022). Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification. Computers, 11(5), 80. https://doi.org/10.3390/computers11050080.
Kang, Y., and Khattak, A. J. (2022). Deep Learning Model for Crash Injury Severity Analysis Using Shapley Additive Explanation Values. Transportation Research Record: Journal of the Transportation Research Board, 2676(12), 242–254. https://doi.org/10.1177/03611981221095087.
Kitali, A. E., Kidando, E., Sando, T., Moses, R., and Ozguven, E. E. (2017). Evaluating Aging Pedestrian Crash Severity with Bayesian Complementary Log–Log Model for Improved Prediction Accuracy. Transportation Research Record, 2659(1). https://doi.org/10.3141/2659-17.
Komol, M. M. R., Hasan, M. M., Elhenawy, M., Yasmin, S., Masoud, M., and Rakotonirainy, A. (2021). Crash severity analysis of vulnerable road users using machine learning. PLOS ONE, 16(8), e0255828. https://doi.org/10.1371/journal.pone.0255828.
Lee, D., Guldmann, J. M., and von Rabenau, B. (2023). Impact of Driver’s Age and Gender, Built Environment, and Road Conditions on Crash Severity: A Logit Modeling Approach. International Journal of Environmental Research and Public Health, 20(3). https://doi.org/10.3390/ijerph20032338.
Lundberg, S. M., Erion, G. G., and Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles.
Lundberg, S. M., and Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 2017-December.
Ali, M. (2020). PyCaret: An open source, low-code machine learning library in Python. https://pycaret.org/.
NHTSA. (2022). Pedestrian Safety: Prevent Pedestrian Crashes. https://www.nhtsa.gov/road-safety/pedestrian-safety.
Rafe, A., and Singleton, P. A. (2023a). CrashAutoML. https://github.com/pozapas/CrashAutoML.
Rafe, A., and Singleton, P. A. (2023b). Exploring Factors Affecting Pedestrian Crash Severity Using TabNet: A Deep Learning Approach. http://arxiv.org/abs/2312.00066.
Rahman, R., Vahedi Saheli, M., and Singleton, P. A. (2023). Risk Factors for Pedestrian Crashes on Utah State Highway Segments: Results from Parametric and Non-Parametric Approaches Controlling for Pedestrian Exposure. Transportation Research Board (TRB) 102nd Annual Meeting.
Salehian, A., Aghabayk, K., Seyfi, M. A., and Shiwakoti, N. (2023). Comparative analysis of pedestrian crash severity at United Kingdom rural road intersections and Non-Intersections using latent class clustering and ordered probit model. Accident Analysis and Prevention, 192. https://doi.org/10.1016/j.aap.2023.107231.
Shrinivas, V., Bastien, C., Davies, H., Daneshkhah, A., and Hardwicke, J. (2023). Parameters influencing pedestrian injury and severity – A systematic review and meta-analysis. Transportation Engineering, 11, 100158. https://doi.org/10.1016/J.TRENG.2022.100158.
Siddiqui, N. A., Chu, X., and Guttenplan, M. (2006). Crossing Locations, Light Conditions, and Pedestrian Injury Severity. Transportation Research Record: Journal of the Transportation Research Board, 1982(1). https://doi.org/10.1177/0361198106198200118.
UDPS. (2023). Utah Crash Summary. https://udps.numetric.net/utah-crash-summary#/.
WHO. (2022). Road traffic injuries. https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries.
Yang, L., Aghaabbasi, M., Ali, M., Jan, A., Bouallegue, B., Javed, M. F., and Salem, N. M. (2022). Comparative Analysis of the Optimized KNN, SVM, and Ensemble DT Models Using Bayesian Optimization for Predicting Pedestrian Fatalities: An Advance towards Realizing the Sustainable Safety of Pedestrians. Sustainability, 14(17), 10467. https://doi.org/10.3390/su141710467.
Information & Authors
Information
Published In
History
Published online: Jun 13, 2024
ASCE Technical Topics:
- Accidents
- Architectural engineering
- Artificial intelligence and machine learning
- Building systems
- Business management
- Computer programming
- Computing in civil engineering
- Infrastructure
- Light (artificial)
- Pedestrians and cyclists
- Practice and Profession
- Public administration
- Public health and safety
- Safety
- Traffic accidents
- Traffic analysis
- Traffic engineering
- Traffic management
- Traffic safety
- Transportation engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.