Autors: Uzunov, H. V., Matzinski, P. G., Uzunov V.H., Dechkova, S. V.
Title: Comparative Analysis of the Proportional Distribution Method and the Random Forest Algorithm for Predicting Pedestrian Traffic Accident Risk
Keywords: accident prevention, expert-based methodology, human factors, Pedestrian safety, Random Forest, risk assessment

Abstract: The risk of pedestrian-involved traffic accidents represents a significant challenge to road safety and necessitates objective methods for analyzing the contributing factors. This study presents a comparative analysis of two methodologies for predicting the risk of pedestrian traffic accidents: a methodology based on proportional risk distribution and the Random Forest algorithm. The analysis utilizes data derived from real court cases, where linguistic variables defined as risk factors are categorized and quantified based on expert evaluations. The results demonstrate that both approaches are applicable for risk assessment, with Random Forest exhibiting higher accuracy and robustness in handling complex and heterogeneous data. Correlation analysis confirms a statistically significant linear relationship between the outputs of the two methods, supporting their validity. Graphical representations derived from the results offer a visual interpretation of risk severity and facilitate comparison between the two approaches. The proposed method is intended for road safety experts, engineers, analysts, and institutions in the field of transportation safety. Its primary aim is to provide an objective and quantitative tool for evaluating the risk factors contributing to pedestrian-related incidents. The method supports informed decision-making regarding preventive measures and awareness campaigns targeting both drivers and pedestrians.

References

  1. D. C. Wilkins, K. M. Kockelman, and N. Jiang, ‘‘Animal-vehicle collisions in texas: How to protect travelers and animals on roadways,’’ Accident Anal. Prevention, vol. 131, pp. 157–170, Oct. 2019, doi: 10.1016/j.aap.2019.05.030.
  2. G. Stamov, I. Stamova, S. Simeonov, and I. Torlakov, ‘‘On the stability with respect to H-Manifolds for Cohen–Grossberg-Type bidirectional associative memory neural networks with variable impulsive perturbations and time-varying delays,’’ Mathematics, vol. 8, no. 3, p. 335, Mar. 2020, doi: 10.3390/math8030335.
  3. T. Gandhi and M. M. Trivedi, ‘‘Pedestrian Protection Systems: Issues, Survey, and Challenges,’’ IEEE Trans. Intell. Transp. Syst., vol. 8, no. 3, pp. 413–430, Sep. 2007, doi: 10.1109/TITS.2007.903444.
  4. A. Theofilatos and G. Yannis, ‘‘A review of the effect of traffic and weather characteristics on road safety,’’ Accident Anal. Prevention, vol. 72, pp. 244–256, Nov. 2014, doi: 10.1016/j.aap.2014.06.017.
  5. Y. Peng, M. Abdel-Aty, Q. Shi, and R. Yu, ‘‘Assessing the impact of reduced visibility on traffic crash risk using microscopic data and surrogate safety measures,’’ Transp. Res. C, Emerg. Technol., vol. 74, pp. 295–305, Jan. 2017, doi: 10.1016/j.trc.2016.11.022.
  6. E. Gospodinova, I. Torlakov, and I. Metodieva, ‘‘Model for forecasting and planning solar energy production using an artificial neural network,’’ in Proc. 3rd Int. Conf. Electr., Comput., Commun. Mechatronics Eng. (ICECCME), Jul. 2023, pp. 1–6, doi: 10.1109/iceccme57830.2023.10252307.
  7. L. Breiman, ‘‘Random forests,’’ Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/a:1010933404324.
  8. J. H. Friedman, ‘‘Greedy function approximation: A gradient boosting machine,’’ Ann. Statist., vol. 29, no. 5, pp. 1189–1232, Oct. 2001, doi: 10.1214/aos/1013203451.
  9. M. A. Quddus, ‘‘Time series count data models: An empirical application to traffic accidents,’’ Accident Anal. Prevention, vol. 40, no. 5, pp. 1732–1741, Sep. 2008, doi: 10.1016/j.aap.2008.06.011.
  10. S. Mokhtarimousavi, J. C. Anderson, A. Azizinamini, and M. Hadi, ‘‘Improved support vector machine models for work zone crash injury severity prediction and analysis,’’ Transp. Res. Record, J. Transp. Res. Board, vol. 2673, no. 11, pp. 680–692, Nov. 2019, doi: 10.1177/0361198119845899.
  11. G. Stamov, S. Simeonov, I. Torlakov, and M. Yaneva, ‘‘Parallel technique on bidirectional associative memory cohen-grossberg neural network,’’ in Recent Contributions To Bioinformatics and Biomedical Sciences and Engineering, vol. 2023. Cham, Switzerland: Springer, pp. 16–20, doi: 10.1007/978-3-031-31069-0_2.
  12. E. Gospodinova and I. Torlakov, ‘‘Information processing with stability point modeling in Cohen–Grossberg neural networks,’’ Axioms, vol. 12, no. 7, p. 612, Jun. 2023, doi: 10.3390/axioms12070612.
  13. M. Xu, H. Yang, and S. Wang, ‘‘Mitigate the range anxiety: Siting battery charging stations for electric vehicle drivers,’’ Transp. Res. C, Emerg. Technol., vol. 114, pp. 164–188, May 2020, doi: 10.1016/j.trc.2020.02.001.
  14. L.-Y. Chang and W.-C. Chen, ‘‘Data mining of tree-based models to analyze freeway accident frequency,’’ J. Saf. Res., vol. 36, no. 4, pp. 365–375, Jan. 2005, doi: 10.1016/j.jsr.2005.06.013.
  15. H. He and E. A. Garcia, ‘‘Learning from imbalanced data,’’ IEEE Trans. Knowl. Data Eng., vol. 21, no. 9, pp. 1263–1284, Sep. 2009, doi: 10.1109/TKDE.2008.239.
  16. D. Delen, R. Sharda, and M. Bessonov, ‘‘Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks,’’ Accident Anal. Prevention, vol. 38, no. 3, pp. 434–444, May 2006, doi: 10.1016/j.aap.2005.06.024.
  17. S. Alkheder, M. Taamneh, and S. Taamneh, ‘‘Severity prediction of traffic accident using an artificial neural network,’’ J. Forecasting, vol. 36, no. 1, pp. 100–108, Jan. 2017, doi: 10.1002/for.2425.
  18. G. Stamov, S. Simeonov, and I. Torlakov, ‘‘Visualization on stability of impulsive Cohen-Grossberg neural networks with time-varying delays,’’ in Contemporary Methods in Bioinformatics and Biomedicine and Their Applications, vol. 2022. Cham, Switzerland: Springer, pp. 195–201, doi: 10.1007/978-3-030-96638-6_21.
  19. G. Stamov, S. Simeonov, and I. Torlakov, ‘‘Software analysis of bidirectional associative memory (BAM) Cohen–Grossberg-Type impulsive neural networks with time-varying delays,’’ in Proc. 7th Int. Congr. Inf. Commun. Technol., 2022, pp. 371–378, doi: 10.1007/978-981-19-2397-5_34.
  20. E. Gospodinova, I. Torlakov, and I. Metodieva, ‘‘Increasing the productivity of an electricity system based on energy generated by hydropower with the help of artificial intelligence,’’ in Proc. 58th Int. Sci. Conf. Inf., Commun. Energy Syst. Technol. (ICEST), Jun. 2023, pp. 205–208, doi: 10.1109/icest58410.2023.10187329.
  21. E. Gospodinova and I. Torlakov, ‘‘Usage of high-performance system in impulsive modelling of hepatitis B virus,’’ in Proc. Intell. Comput., 2023, pp. 373–385, doi: 10.1007/978-3-031-37963-5_26.
  22. H. Harirforoush and L. Bellalite, ‘‘A new integrated GIS-based analysis to detect hotspots: A case study of the city of sherbrooke,’’ Accident Anal. Prevention, vol. 130, pp. 62–74, Sep. 2019, doi: 10.1016/j.aap.2016.08.015.
  23. H. Huang and M. Abdel-Aty, ‘‘Multilevel data and Bayesian analysis in traffic safety,’’ Accident Anal. Prevention, vol. 42, no. 6, pp. 1556–1565, Nov. 2010, doi: 10.1016/j.aap.2010.03.013.
  24. J. Tang, F. Liu, Y. Zou, W. Zhang, and Y. Wang, ‘‘An improved fuzzy neural network for traffic speed prediction considering periodic characteristic,’’ IEEE Trans. Intell. Transp. Syst., vol. 18, no. 9, pp. 2340–2350, Sep. 2017, doi: 10.1109/TITS.2016.2643005.
  25. M. D. Nguyen and M. T. Nguyen, ‘‘Artificial intelligence for human detection, identification and tracking: Methods and applications,’’ J. Future Artif. Intell. Technol., vol. 2, no. 1, pp. 79–94, Apr. 2025, doi: 10.62411/faith.3048-3719-87.
  26. S. Kumar, S. C. Sharma, and R. Kumar, ‘‘Wireless sensor network based real-time pedestrian detection and classification for intelligent transportation system,’’ Int. J. Math., Eng. Manage. Sci., vol. 8, no. 2, pp. 194–212, Apr. 2023, doi: 10.33889/ijmems.2023.8.2.012.
  27. R. Yu and M. Abdel-Aty, ‘‘Investigating the different characteristics of weekday and weekend crashes,’’ J. Saf. Res., vol. 46, pp. 91–97, Sep. 2013, doi: 10.1016/j.jsr.2013.05.002.
  28. S. Gao, Q. Ran, Z. Su, L. Wang, W. Ma, and R. Hao, ‘‘Evaluation system for urban traffic intelligence based on travel experiences: A sentiment analysis approach,’’ Transp. Res. A, Policy Pract., vol. 187, Sep. 2024, Art. no. 104170, doi: 10.1016/j.tra.2024.104170.
  29. J. Y. Yang, E. Liang, Z. Su, Z. Zou, P. Zhen, J. Guo, W. Ma, and K. An, ‘‘DFF: Decision-focused fine-tuning for smarter predict-then-optimize with limited data,’’ in Proc. AAAI Conf. Artif. Intell., 2025, vol. 39, no. 25, pp. 26868–26876.

Issue

IEEE Access, vol. 13, pp. 129828-129844, 2025, Albania, https://doi.org/10.1109/ACCESS.2025.3591297

Цитирания (Citation/s):
1. Hamdan N., Sipos T., Predicting Segment-Level Road Traffic Injury Counts Using Machine Learning Models: A Data-Driven Analysis of Geometric Design and Traffic Flow Factors, 2025, Future Transportation, issue 4, vol. 5, DOI 10.3390/futuretransp5040197, eissn 26737590 - 2025 - в издания, индексирани в Scopus

Вид: статия в списание, публикация в реферирано издание, индексирана в Scopus и Web of Science