Automotive Experiences

Articles

Modeling Causal Analysis of Crash Severity on Indonesian Toll Road Using Integrated Z-Score and Bayesian Network Framework

Bambang Istiyanto , Pratikso , Rachmat Mudiyono , Hafidz Nurrohman

Published
March 31, 2026

Vol. 9 No. 1 (2026)
Pages 107-121

DOI

Open Access
Share

Abstract

Traffic crashes remain a critical safety challenge, with Indonesia experiencing 73,446 fatalities annually. This study develops an integrated Z-Score and Bayesian Network framework to analyze causal interactions between human and environmental factors influencing crash severity on toll roads. Z-Score analysis of 450 crash records (2022”“2025) identified five statistically significant blackspot segments, with KM 430”“431 exhibiting the highest concentration (Z = 4.036, n = 91). A Bayesian Network model constructed using K2 structure learning and Expectation-Maximization parameter estimation achieved 86.2% classification accuracy, surpassing previous international applications (78”“82%). Conditional probability analysis revealed that straight-downhill segments exhibited 3.3-fold higher fatal crash probability than straight-level segments (0.083 vs. 0.025), while night-time conditions increased fatal risk by 57%. Sensitivity analysis demonstrated that crash type (weighted index = 0.282) and accident cause (0.214) exerted strongest influence on severity outcomes. Human error constituted 83% of crashes but showed moderate sensitivity, indicating that severe outcomes emerge from interactions between human factors and adverse conditions rather than isolated factors. Findings support prioritizing enhanced lighting and speed management on curved-downhill segments during night-time, alongside rear-end collision prevention strategies. This validated framework enables evidence based, proactive crash management and intervention prioritization for toll road safety in developing countries.

Keywords

Crash severity; Road safety; Bayesian network; Z-score

References

  1. [1] T. Sagamiko and N. Mbare, “Modelling Road Traffic Accidents Counts in Tanzania: A Poisson Regression Approach,” Tanzania Journal of Science, vol. 47, no. 1, pp. 308–314, 2021, doi: 10.4314/tjs.v47i1.26.
  2. [2] Z. Hu, J. Zhou, and E. Zhang, “Improving Traffic Safety through Traffic Accident Risk Assessment,” Sustainability, vol. 15, no. 4, p. 3748, Feb. 2023, doi: 10.3390/su15043748.
  3. [3] World Health Organization, “Global status report on road safety 2018,” Geneva, 2018.
  4. [4] U. N. G. Assembly, “Resolution A/RES/74/299: Improving Global Road Safety,” New York, 2020.
  5. [5] World Health Organization, “Road Traffic Injuries: Global Facts and 2030 Reduction Target,” Geneva, Switzerland, 2025.
  6. [6] A. Iranitalab and A. Khattak, “Comparison of four statistical and machine learning methods for crash severity prediction,” Accident Analysis and Prevention, vol. 108, no. August, pp. 27–36, 2017, doi: 10.1016/j.aap.2017.08.008.
  7. [7] X. Zou and W. L. Yue, “A Bayesian Network Approach to Causation Analysis of Road Accidents Using Netica,” Journal of Advanced Transportation, vol. 2017, pp. 1–18, 2017, doi: 10.1155/2017/2525481.
  8. [8] C. Carrodano, “Data-driven risk analysis of nonlinear factor interactions in road safety using Bayesian networks,” Scientific Reports, vol. 14, no. 1, p. 18948, Aug. 2024, doi: 10.1038/s41598-024-69740-6.
  9. [9] Y.-J. Joo, S.-Y. Kho, D.-K. Kim, and H.-C. Park, “A data-driven Bayesian network for probabilistic crash risk assessment of individual driver with traffic violation and crash records,” Accident Analysis & Prevention, vol. 176, p. 106790, Oct. 2022, doi: 10.1016/j.aap.2022.106790.
  10. [10] D. Lord and F. Mannering, “The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives,” Transportation Research Part A: Policy and Practice, vol. 44, no. 5, pp. 291–305, Jun. 2010, doi: 10.1016/j.tra.2010.02.001.
  11. [11] R. Ullah Khan, J. Yin, and F. Shair Mustafa, “Factors Affecting Crash Frequencies: A Negative Binomial Regression Based Analysis of Indus Highway, Pakistan,” MATEC Web of Conferences, vol. 296, p. 01005, Oct. 2019, doi: 10.1051/matecconf/201929601005.
  12. [12] S. A. Arhin and A. Gatiba, “Predicting Injury Severity of Angle Crashes Involving Two Vehicles at Unsignalized Intersections Using Artificial Neural Networks,” Engineering, Technology & Applied Science Research, vol. 9, no. 2, pp. 3871–3880, Apr. 2019, doi: 10.48084/etasr.2551.
  13. [13] K. Assi, S. M. Rahman, U. Mansoor, and N. Ratrout, “Predicting Crash Injury Severity with Machine Learning Algorithm Synergized with Clustering Technique: A Promising Protocol,” International Journal of Environmental Research and Public Health, vol. 17, no. 15, p. 5497, Jul. 2020, doi: 10.3390/ijerph17155497.
  14. [14] Y. Oktopianto, S. Shofiah, F. A. Rokhman, K. P. Wijayanthi, and E. Krisdayanti, “Analisis Daerah Rawan Kecelakaan (Black Site) Dan Titik Rawan Kecelakaan (Black Spot) Provinsi Lampung,” Borneo Engineering : Jurnal Teknik Sipil, vol. 5, no. 1, pp. 40–51, Apr. 2021, doi: 10.35334/be.v5i1.1777.
  15. [15] B. Kristanto, S. Widodo, and Sumiyattinah, “Analisis Daerah Rawan Kecelakaan (Drk) Dan Titik Rawan Kecelakaan Di Kabupaten Melawi Provinsi Kalimantan Barat,” JeLAST: Jurnal Teknik Kelautan, PWK, Sipil, dan Tambang, vol. 11, no. 3, 2024, doi: 10.26418/jelast.v11i3.84793.
  16. [16] Rifky Aldila Primasworo, M. Sa’dillah, and Maria Goreti Ganjom, “Analysis of Accident Rate in Kolonel Sugiono Street, Malang City,” Cantilever: Jurnal Penelitian dan Kajian Bidang Teknik Sipil, vol. 13, no. 1, pp. 73–80, Aug. 2024, doi: 10.35139/cantilever.v13i1.268.
  17. [17] I. Babaev and S. Kanarachos, “Bayesian Networks in a Road Accident Severity Estimation,” SSRN Electronic Journal, 2023, [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4329676
  18. [18] A. Kusumawati, K. N. S. Ayuningtyas, and I. Hadiyanti, “Modelling Single-Vehicle Crash Occurrences on Indonesian Toll Roads,” Journal of Road Safety, vol. 36, no. 4, Nov. 2025, doi: 10.33492/JRS-D-25-4-2120803.
  19. [19] F. S. Didin et al., “Analysis of Influencing Factor for Rear-end Crash on Toll Road: An Examination Using Self-reported Questionnaires,” The Open Transportation Journal, vol. 18, no. 1, Nov. 2024, doi: 10.2174/0126671212362811241114115504.
  20. [20] Y. Liang et al., “Nonlinear effects of traffic statuses and road geometries on highway traffic accident severity: A machine learning approach,” PLOS ONE, vol. 19, no. 11, p. e0314133, Nov. 2024, doi: 10.1371/journal.pone.0314133.
  21. [21] W. Santosa et al., Perspektif Kebijakan dalam Pembangunan Jalan Tol di Indonesia. Jakarta: PT Penjaminan Infrastruktur Indonesia (Persero), 2023.
  22. [22] N. N. A. Efendi, “Faktor Human Error Masih Dominasi Penyebab Kecelakaan di Jalan Tol,” Grid Oto. [Online]. Available: https://www.gridoto.com/read/221901971/faktor-human-error-masih-dominasi-penyebab-kecelakaan-di-jalan-tol
  23. [23] B. Istiyanto, Y. E. R. Unzilatirrizqi D, M. D. R. Dewantoro, and R. Ahmad, “Geographic Information System (GIS-T) database design for transportation safety system (case study: spatial database for road transportation system in Indonesia),” IOP Conference Series: Earth and Environmental Science, vol. 1117, no. 1, p. 012023, Dec. 2022, doi: 10.1088/1755-1315/1117/1/012023.
  24. [24] B. Istiyanto and D. Widitasari, “Road safety analysis on Srondol – Jatingaleh highway, using Crash Modification Factors (CMFs) Case study: Semarang City, Central Java, Indonesia,” IOP Conference Series: Earth and Environmental Science, vol. 202, p. 012005, Nov. 2018, doi: 10.1088/1755-1315/202/1/012005.
  25. [25] J. Siswanto et al., “Deep learning-based LSTM model for number of road accidents prediction,” in AIP Conference Proceedings, 2025, p. 050004. doi: 10.1063/5.0258529.
  26. [26] L. BayesFusion, “GeNIe Academic: Decision Modeling Environment for Bayesian Networks and Influence Diagrams,” 2024, BayesFusion, LLC, Pittsburgh, Pennsylvania, USA.
  27. [27] K. G. Olesen and A. L. Madsen, “Maximal prime subgraph decomposition of Bayesian networks,” IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), vol. 32, no. 1, pp. 21–31, 2002, doi: 10.1109/3477.979956.
  28. [28] M. Wu, D. Shan, Z. Wang, X. Sun, J. Liu, and M. Sun, “A Bayesian Network Model for Real-time Crash Prediction Based on Selected Variables by Random Forest,” in 2019 5th International Conference on Transportation Information and Safety (ICTIS), IEEE, Jul. 2019, pp. 670–677. doi: 10.1109/ICTIS.2019.8883694.
  29. [29] M. Sun, R. Zhou, C. Jiao, and X. Sun, “Severity Analysis of Hazardous Material Road Transportation Crashes with a Bayesian Network Using Highway Safety Information System Data,” International Journal of Environmental Research and Public Health, vol. 19, no. 7, p. 4002, Mar. 2022, doi: 10.3390/ijerph19074002.
  30. [30] P. Lumba, I. Muthohar, and S. Priyanto, “Human Factors on Motorcyclists’ Accidents Severity; Analysis Using Bayesian Network,” International Journal of Engineering and Technology, vol. 9, no. 1, pp. 233–242, Feb. 2017, doi: 10.21817/ijet/2017/v9i1/170901425.
  31. [31] W. Liao and Q. Ji, “Learning Bayesian network parameters under incomplete data with domain knowledge,” Pattern Recognition, vol. 42, no. 11, pp. 3046–3056, Nov. 2009, doi: 10.1016/j.patcog.2009.04.006.
  32. [32] Y. Peng, L. Cheng, Y. Jiang, and S. Zhu, “Examining Bayesian network modeling in identification of dangerous driving behavior,” PLOS ONE, vol. 16, no. 8, p. e0252484, Aug. 2021, doi: 10.1371/journal.pone.0252484.
  33. [33] S. Demissie, M. P. LaValley, N. J. Horton, R. J. Glynn, and L. A. Cupples, “Bias due to missing exposure data using complete‐case analysis in the proportional hazards regression model,” Statistics in Medicine, vol. 22, no. 4, pp. 545–557, Feb. 2003, doi: 10.1002/sim.1340.
  34. [34] S. Al Sulaie, “Sensitivity Analysis of Factors Affecting Consequences Due to Traffic Crashes: A Bayesian Network Modelling,” Journal of Road Safety, vol. 36, no. 1, pp. 11–20, Feb. 2025, doi: 10.33492/JRS-D-25-1-2442769.
  35. [35] J. De Oña, G. López, R. Mujalli, and F. J. Calvo, “Analysis of traffic accidents on rural highways using Latent Class Clustering and Bayesian Networks,” Accident Analysis and Prevention, vol. 51, pp. 1–10, 2013, doi: 10.1016/j.aap.2012.10.016.
  36. [36] R. S. Pilla, “Alternative EM methods for nonparametric finite mixture models,” Biometrika, vol. 88, no. 2, pp. 535–550, Jun. 2001, doi: 10.1093/biomet/88.2.535.
Article Metrics
59
Views
29
Downloads

SCITE

DIMENSIONS

Publication Information
Published March 31, 2026
Section Articles
Copyright Copyright (c) 2026 Bambang Istiyanto, Pratikso Pratikso, Rachmat Mudiyono, Hafidz Nurrohman
Keywords
  • Crash severity
  • Road safety
  • Bayesian network
  • Z-score