Comparing Performance of Different Machine Learning Methods for Predicting Severity of Construction Work Zone Crashes
Publication: Computing in Civil Engineering 2023
ABSTRACT
In 2020, more than 102,000 work zone crashes occurred in the United States, resulting in over 45,000 injuries and more than 850 fatalities. These numbers are higher than 2019 records, despite lower traffic volumes due to the COVID-19 pandemic. Also, population growth and the increased load on infrastructure are expected to lead to more construction work zones and, consequently, more crashes and fatalities in the future. As such, understanding the factors contributing to work zone crashes and their severity can assist the Department of Transportation (DOT) in safety management and planning. Accordingly, this study investigated the effect of freeway construction work zones on the severity of crashes by employing machine learning algorithms. Moreover, the performance of three of the most common machine learning models, decision tree, random forest (RF), and XGBoost, were evaluated based on accuracy, precision, recall, and F1-score. The model was developed using crash data and work zone information from the state of Utah between 2017 and 2021, considering an extensive set of work zone attributes, such as road factors, environmental conditions, driver attributes, and work zone features. The study results showed that RF has the best performance in severity classification, achieving an accuracy of 88.6%. Moreover, feature importance analysis reveals that roadway surface conditions, crash type, motorcycle involvement, weather conditions, and roadway junction type are significant contributors to work zone crash severity. The findings of this study provide valuable insights for the analysis of construction work zone crashes and DOT’s safety management plans.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Alkheder, S., Taamneh, M., and Taamneh, S. (2017). Severity prediction of traffic accident using an artificial neural network. Journal of Forecasting, 36(1), 100–108.
Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K., Mitchell, R., Cano, I., and Zhou, T. (2015). Xgboost: extreme gradient boosting. R Package Version 0.4-2, 1(4), 1–4.
Cheng, C.-F., Rashidi, A., Davenport, M. A., and Anderson, D. V. (2017). Activity analysis of construction equipment using audio signals and support vector machines. Automation in Construction, 81, 240–253.
Islam, M. (2022). An analysis of motorcyclists' injury severities in work-zone crashes with unobserved heterogeneity. IATSS Research.
Mashhadi, A. H., Farhadmanesh, M., Rashidi, A., and Marković, N. (2021a). Review of methods for estimating construction work zone capacity. Transportation Research Record, 2675(9), 382–397.
Mashhadi, A. H., Farhadmanesh, M., Rashidi, A., and Marković, N. (2021b). State-of-the-Art Methods in Estimating Freeway Work zones Capacity: A Literature Review. Transportation Research Board 100th Annual MeetingTransportation Research Board, TRBAM-21-01863.
Mashhadi, A. H., and Rashidi, A. (2021). Evaluating Mobility Impacts Of Construction Workzones On Utah Transportation System Using Machine Learning Techniques. National Institute for Transportation and Communities (NITC).
Mohammadi, P., Rashidi, A., Malekzadeh, M., and Tiwari, S. (2023). Evaluating various machine learning algorithms for automated inspection of culverts. Engineering Analysis with Boundary Elements, 148, 366–375.
Mokhtarimousavi, S., Anderson, J. C., Azizinamini, A., and Hadi, M. (2019). Improved support vector machine models for work zone crash injury severity prediction and analysis. Transportation Research Record, 2673(11), 680–692.
Mokhtarimousavi, S., Azizinamini, A., and Hadi, M. (2020). Severity of worker-involved work zone crashes: A study of contributing factors. International Conference on Transportation and Development 2020, 47–59.
Santos, B., Trindade, V., Polónia, C., and Picado-Santos, L. (2021). Detecting risk factors of road work zone crashes from the information provided in police crash reports: the case study of Portugal. Safety, 7(1), 12.
Sze, N. N., and Song, Z. (2019). Factors contributing to injury severity in work zone related crashes in New Zealand. International Journal of Sustainable Transportation, 13(2), 148–154.
Work Zone Crashes, Injuries, & Fatalities - Facts & Data | Work Zone Barriers Guide. (n.d.). Retrieved March 8, 2023, from https://www.workzonebarriers.com/work-zone-crash-facts.html.
Yahaya, M., Fan, W., Fu, C., Li, X., Su, Y., and Jiang, X. (2020). A machine-learning method for improving crash injury severity analysis: a case study of work zone crashes in Cairo, Egypt. International Journal of Injury Control and Safety Promotion, 27(3), 266–275.
Zhang, K., and Hassan, M. (2019a). Identifying the factors contributing to injury severity in work zone rear-end crashes. Journal of Advanced Transportation, 2019.
Zhang, K., and Hassan, M. (2019b). Injury severity analysis of nighttime work zone crashes. 2019 5th International Conference on Transportation Information and Safety (ICTIS), 1301–1308.
Information & Authors
Information
Published In
History
Published online: Jan 25, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Business management
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction industry
- Construction management
- Construction methods
- Construction sites
- Highway and road conditions
- Highway and road management
- Highway transportation
- Highways and roads
- Infrastructure
- Infrastructure construction
- Occupational safety
- Practice and Profession
- Public administration
- Public health and safety
- Safety
- Traffic accidents
- Traffic engineering
- Traffic management
- Transportation engineering
- Work zones
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.