A Machine Learning Method for Improving the Safety of Pedestrians on Roadways

Year : 2024 | Volume : 11 | Issue : 01 | Page :
    By

    Shahin Mirbakhsh,

  • Mahdi Azizi,

  1. Student, Department of Civil and Environmental Engineering, Shahid Chamran University of Ahvaz., ,
  2. Student, Department of Civil and Environmental Engineering, Shahid Chamran University of Ahvaz., ,

Abstract

An essential aspect of enhancing road safety involves predicting road accidents and identifying risk factors linked to severe injuries. This can be achieved through two distinct methods: machine learning and statistical approaches. This study leverages machine learning techniques to assess the severity of injuries pedestrians sustain in road traffic collisions. While statisticians aim to model and understand connections between variables, machine learning tackles more complex datasets to create algorithms capable of pattern recognition and prediction without explicit programming. Machine learning offers advantages such as handling large datasets, adaptability to various data sources and tasks, and automation of pattern recognition and prediction tasks, reducing manual involvement and enabling rapid processing of vast amounts of data. Moreover, machine learning models can be continuously updated and refined with new data to improve accuracy over time, unlike conventional statistical techniques which may struggle with nonlinear interactions between variables. The study begins by compiling a comprehensive list of features related to both accidents and environmental factors, with a focus on those most influential on pedestrian injury severity. Selecting the best algorithm involves evaluating its performance metrics, including accuracy, precision, recall, and F1 score. It’s crucial to highlight that the developed model is not static; it requires regular updates and retraining using new accident data to reflect changes in the road environment, driver behavior, and pedestrian conduct. While the current model is based on Israeli data and predicts injury outcomes within Israel, for broader applicability, it should undergo retraining and evaluation using traffic accident data specific to the relevant country or region.

Keywords: Safety of pedestrians, machine learning method, road safety, road accidents, identifying risk factors

[This article belongs to Journal of Industrial Safety Engineering ]

How to cite this article:
Shahin Mirbakhsh, Mahdi Azizi. A Machine Learning Method for Improving the Safety of Pedestrians on Roadways. Journal of Industrial Safety Engineering. 2024; 11(01):-.
How to cite this URL:
Shahin Mirbakhsh, Mahdi Azizi. A Machine Learning Method for Improving the Safety of Pedestrians on Roadways. Journal of Industrial Safety Engineering. 2024; 11(01):-. Available from: https://journals.stmjournals.com/joise/article=2024/view=156953


References

1. PEDESTRIAN SAFETY, A road safety manual for decision-makers and practitioners, in:Pedestrian Safety: a Road Safety Manual for Decision-Makers and Practitioners, second ed., World Health Organization, Geneva, 2023. https://apps.who.int/iris/bitstream/handle/10665/367419/978924 0072497-eng.pdf?sequence=1.
2. 27 Jan, Traffic Prediction: How Machine Learning Helps Forecast Congestions and Plan Optimal Routes, 2022, https://www.altexsoft.com/.
3. S. Birfir, A. Elalouf, T. Resenbloom, Building machine-learning models for reducing the severity of bicyclist road traffic injuries, Tranpostation engineering 12 (2023). June 2023.
4. NHTSA. Traffic Safety Facts: Pedestrians. National Highway Traffic Safety Administration,
Washington (DC). Report No.: DOT HS 812 681.
5. A. Behnood, F. Mannering, The temporal stability of factors affecting driver-injury severities in single-vehicle crashes: Some empirical evidence (2015).
6. N. Ahmad, A. Ahmed, B. Wali, T.U. Saeed, Exploring factors associated with crash severity on motorways in Pakistan, in: Proceedings of the Institution of Civil Engineers – Transport 04,2019,pp. 1–20, https://doi.org/10.1680/jtran.18.00032.
7. M. Taamneh, S. Alkheder, S. Taamneh, Data-mining techniques for traffic accident modeling and prediction in the United Arab Emirates, J. Transport. Saf.Secur. 9 (2017) 146–166.
8. R. Mujalli, J. De Ona, A method for simplifying the analysis of traffic accidents injury severity on two-lane highways using bayesian networks, J. Saf. Res. 42(2011) 317–326.
9. S. Dong, J. Zhou, A comparative study on drivers’ stop/go behavior at signalized intersections based on decision tree classification model, J. Adv. Transport.(2020) 1–13.
10. Z. Liu, H. Chen, Y. Li, Q. Zhang, Taxi demand prediction based on a combination forecasting model in hotspots, J. Adv. Transport. (2020) 1–13.
11. J. Abell′an, G. L′opez, J. De ̃Ona, Analysis of traffic accident severity using decision rules via decision trees, Expert Syst. Appl. 40 (2013) 6047–6054.
12. N. Dong, H. Huang, L. Zheng, Support vector machine in crash prediction at the level of traffic analysis zones: assessing the spatial proximity effects, Accid. Anal.Prev. 82 (2015) 192–198.
13. T. Anderson, Kernel density estimation and k-means clustering to profile road accident hotspots, Accid. Anal. Prev. 41 (2009) 359–364.
14. Q. Zeng, H. Huang, A stable and optimized neural network model for crash injury severity prediction, Accid. Anal. Prev. 73 (2014) 351–358.
15. J.K. Kim, G.F. Ulfarsson, V.N. Shankar, S. Kim, Age and pedestrian injury severity in motor-
vehicle crashes: a heteroskedastic logit analysis, Accid. Anal. Prev.40 (5) (2008) 1695–1702.
16. L.F. Beck, L.J. Paulozzi, S.C. Davidson, Pedestrian fatalities, Atlanta metropolitan statistical area and United States, 2000–2004, J. Saf. Res. 38 (6) (2007)613–616.
17. D.F. Preusser, J.K. Wells, A.F. Williams, H.B. Weinstein, Pedestrian crashes in Washington DC and baltimore, Accid. Anal. Prev. 34 (5) (2002) 703–710.
18. M.M. Mabunda, L.A. Swart, M. Seedat, Magnitude and categories of pedestrian fatalities in South Africa, Accid. Anal. Prev. 40 (2) (2008) 586–593.
19. M.F. Ballesteros, P.C. Dischinger, P. Langenberg, Pedestrian injuries and vehicle type in
Maryland1995–1999, Accid. Anal. Prev. 36 (1) (2004) 73–81.
20. R.J. Schneider, R.M. Ryznar, A.J. Khattak, An accident waiting to happen: a spatial approach to proactive pedestrian planning, Accid. Anal. Prev. 36 (2004)193–211.
21. C. Lee, M. Abdel-Aty, Comprehensive analysis of vehicle-pedestrian crashes at intersections in Florida, Accid. Anal. Prev. 37 (2005) 775–786.
22. Dipanjan Mukherjee, Sudeshna Mitra, A comprehensive study on identification of risk factors for fatal pedestrian crashes at urban intersections in a developing country, Asian Transport Studies(2020).
23. A.S. Al-Ghamdi, Pedestrian-vehicle crashes and analytical techniques for stratified contingency tables, Accid. Anal. Prev. 34 (2002) 205–214.
24. A. Wazana, V.L. Rynard, P. Raina, P. Krueger, Are child pedestrians at increased risk of injury on one-way compared to two-way streets? Can. J. Public Health 91(2000) 201–206.
25. Alexander Ganichev, Oksana Batishcheva, Evaluating the conflicts between vehicles and
pedestrians, Transport. Res. Procedia 50 (2020) (2020) 145–151.
26. Abbas Sheykhfardab, Farshidreza Haghig, Analysis of the occurrence and severity of vehicle-pedestrian conflicts in marked and unmarked crosswalks through naturalistic driving study,Transport. Res. F Traffic Psychol. Behav. 76 (2021) 178–192.
27. Johan Vos, Haneen Farah, Speed Behavior upon Approaching Freeway Curves, vol. 159, Accident Analysis and Prevention, 2021.
28. Jun Xua, Yibing Lia, Reconstruction model of vehicle impact speed in pedestrian–vehicle accident,Int. J. Impact Eng. 36 (6) (2009) 783–788.
29. Seyedmirsajad Mokhtarimousavi, Jason C. Anderson, Factors affecting injury severity in vehicle-pedestrian crashes: A day-of-week analysis using random parameter ordered response models and Artificial Neural Networks International Journal of Transportation Science and Technology 9 (2)(2020) 100–115.
30. Liu, L., Xue, J., Mahdi, M., Mirbakhsh, S., Du, Q. (2023). Enhanced Automated Intersection Control for Platooning AVs: A Fusion Model with Significant Traffic, Safety, and Environmental Improvements. J Electrical Electron Eng, 2(4), 359-367.
31. Kadkhodayi, A., Jabeli, M., Aghdam, H., Mirbakhsh, S. (2023). Artificial Intelligence-Based Real-Time Traffic Management. J Electrical Electron Eng, 2(4), 368-373.
32. Mirbakhsh, Ardeshir, Joyoung Lee, and Dejan Besenski. “Spring–mass–damper-based platooning logic for automated vehicles.” Transportation research record 2677.5 (2023): 1264-1274.
33. Mirbakhsh, Ardeshir. A Self-Learning Intersection Control System for Connected and Automated Vehicles. Diss. New Jersey Institute of Technology, 2022.
34. Mirbakhsh, Ardeshir. “How hospitals response to disasters; a conceptual deep reinforcement learning approach.” (2023).

Regular Issue Subscription Original Research
Volume 11
Issue 01
Received 15/05/2024
Accepted 27/06/2024
Published 28/06/2024
Retracted 08/02/2025
Publication Time 44 Days
669

Login


My IP

PlumX Metrics