Journal of Transportation Research

Journal of Transportation Research

Analysis of the Role of Pedestrian Infrastructure in Pedestrian Accidents Using Machine Learning Algorithms (Case Study: Isfahan City)

Document Type : Original Article

Authors
Rasoul Zabihian 1
Mohammad Reza Ahadi 2
Ali Naderan 3
1 Ph.D., Department of Civil Engineering, Ki.C., Islamic Azad University, Kish, Iran.
2 Transportation Research Institute, Road, Housing and Urban Development Research Center, Tehran, Iran.
3 Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
10.22034/tri.2026.607313.3532
Abstract
The primary goal of this study is to assess the role of pedestrian infrastructure, particularly sidewalk width, in influencing pedestrian accidents in the city of Isfahan. The study aims to analyze how various infrastructure-related factors, including sidewalk width, contribute to pedestrian safety and accident frequency in urban environments, with a focus on the dynamic between pedestrian movement and vehicular traffic. Machine learning algorithms were employed within MATLAB software to process and analyze infrastructure and pedestrian accident data collected from various districts of Isfahan. Multiple variables were considered, including sidewalk width, speed limits, distance between parking lots and sidewalks, sidewalk quality, number of bus stops, intersections, and pedestrian lanes.The analysis revealed that sidewalk width is the most significant factor affecting pedestrian accidents, accounting for approximately 35% of the effect on accident frequency. Wider sidewalks were found to provide more space for pedestrian movement, reducing congestion and minimizing interactions with vehicles, thus lowering accident risks. Other factors, such as speed limits, parking lot proximity, sidewalk quality,The study strongly emphasizes the importance of improving pedestrian infrastructure, particularly by expanding and maintaining adequate sidewalk widths, as a key strategy for reducing pedestrian accidents. Enhancing sidewalk design not only improves pedestrian safety but also contributes to better public space quality, encourages walking, and promotes more sustainable urban environments. The findings advocate for urban planners, civil engineers, and policymakers to prioritize sidewalk improvements in their urban planning and transportation infrastructure strategies to create safer and more livable cities.
Keywords
Pedestrian Infrastructure
Sidewalk Width
Pedestrian Accidents
Machine Learning
Subjects
- Ahmadzadeh Jokandan, N., Sheikh Fard, A., & Haghigi, F. R. (2022). Identifying potential risk factors for pedestrian accidents in Gilan province using structural equation modeling. Traffic Engineering, 88, 1-14.
- Amouzadeh Omrani, M., & Fadallah, M. R. (2023). Evaluation of factors affecting pedestrian accident severity on urban streets and proposing a model for predicting these accidents (Case study: City of Qazvin). Jadid Road Journal, 3, 83-102.
 - Babić, D., Babić, D., Fiolić, M., & Ferko, M. (2021). Factors affecting pedestrian conspicuity at night: Analysis based on driver eye tracking. Safety science, 139, 105257.‏
- Bakhtiyari, M., Delpisheh, A., Monfared, A.B., Kazemi-Galougahi, M.H., Mehmandar, M.R.,
- Bao, J., Liu, P., & Ukkusuri, S. V. (2019).A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source data. Accident Analysis & Prevention, 122, 239-254.‏
- Brewster, S. E., Elliott, M. A., & Kelly, S. W. (2015). Evidence that implementation intentions reduce drivers’ speeding behavior: testing a new intervention to change driver behavior. Accident Analysis & Prevention, 74, 229-242.‏
- D., 2006. Road traffic injury prevention training manual. World Health Organization, Geneva.
- Edrisi, A. (2002). Modeling factors affecting the severity and frequency of truck accidents on two-lane rural roads using logit models and neural networks. Master’s thesis in Road and Transportation Engineering, Sharif University of Technology.
- Farsi Poor, H. (1999). Review of pedestrian safety status in the country. Journal of Traffic News,1(3-4), 6-11.
- Huang, H., Zeng, Q., Pei, X., Wong, S. C., & Xu, P. (2016). Predicting crash frequency using an optimised radial basis function neural network model. Transportmetrica A: Transport Science, 12(4), 330-345.‏
- Jadaan, K. S., Al-Fayyad, M., & Gammoh, H. F. (2014). Prediction of road traffic accidents in Jordan using artificial neural network (ANN). Journal of Traffic and Logistics Engineering, 2(2).‏
- Karami, A., Haji Hosseini, M., & Abbasi, M. H. (2018). Proposing a pedestrian accident prediction model at intersections in the city of Isfahan. Conference on Civil Engineering, Architecture, and Urban Planning in the Islamic Countries.
-­Khalesdadian, H. (2018). Investigation of pedestrian accident factors and solutions for their reduction: A case study of the city of Ghorveh. International Conference on Civil Engineering, Architecture, and Urban Development in Iran.
- Khayyati Kivi, A. H., Barg Gol, I., & Hamedi, G. (2021). Evaluation of pedestrian accident severity on rural roads using cluster analysis. 8th National Conference on Sustainable Development in Civil Engineering.
-­Khosrowmehr, A., & Davoodi, S. R. (2017). Investigation and ranking of pedestrian accident causes and evaluation of appropriate solutions (Case study: City of Gorgan). First National Conference on Road and Transportation Engineering.
-­­Ki Manesh, M. R., & Zabihian, R. (2023). Evaluation of factors affecting pedestrian accidents in urban streets and proposing a model for predicting these accidents (Case study: City of Zanjan). Transportation Research Journal, 3, 171-190.
- Lobo, A., Ferreira, S., Iglesias, I., & Couto, A. (2020). Daily and Latent Lagged Effects of Rainfall on Pedestrian–Vehicle Collisions. Weather, climate, and society, 12(2), 279-291.‏
- Ministry of Housing and Urban Development. (1996). Urban road design regulations - Section 10: Pedestrian paths.
-­Mirzaei, B., Shad, R., & Mohammadzadeh Moghadam, A. (2022). Assessment of spatial distribution of pedestrian accidents among the elderly using GIS (Case study: City of Mashhad). Traffic Engineering, 89, 15-25.
- Moeinaddini, M., Asadi-Shekari, Z., Zaly Shah, M., )2014(. The relationship between urban street.
-­Mokhtarimousavi, S., Anderson, J. C., Azizinamini, A., & Hadi, M. (2020). 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), 100-115.‏
- Najafi Moghaddam Gilani, V., Mohammadpour, H., & Hosseinian, M. (2021). Analysis and study of pedestrian accidents on rural roads connected to the city of Rasht and providing safety solutions to reduce traffic accidents. Gilan Police Journal, 39, 91-108.
-­Noland, R.B., Oh, L., 2004. The effect of infrastructure and demographic change on traffic-related.
-­Prasannakumar, V., Vijith, H., Charutha, R., Geetha, N., 2011. Spatio-Temporal Clustering of Road Accidents: GIS Based Analysis and Assessment. Int. Conf. Spat. Think. Geogr. Inf. Sci. 2011 21 0, 317–325.
doi:10.1016/j.sbspro.2011.07.020
- Shahgholi, M. S., & Kargar, B. (2023). Spatial analysis of pedestrian accidents in District 5 of Isfahan city. Geographical Journal of Sazeman, 78, 21-39.
- Solai, M. (1993). Studies and analysis of vehicle accidents with pedestrians in urban areas. Master’s thesis in Road and Transportation Engineering, Iran University of Science and Technology.
- Ulak, M. B., Kocatepe, A., Yazici, A., Ozguven, E. E., & Kumar, A. (2021). A stop safety index to address pedestrian safety around bus stops. Safety Science, 133, 105017.‏
 - Zegeer, Charles V. & J. Richard Stewart & Herman Huang & Peter Lagerwey­ (2001). Safety Effects of Marked Versus Unmarked Crosswalks at Uncontrolled Locations. Transportation Research Record, No. 1773, 56-68.
- Zeng, Q., & Huang, H. (2014). Bayesian spatial joint modeling of traffic crashes on an urban road network. Accident Analysis & Prevention, 67, 105-112.‏
-Abbas, M. S. (2023). Accident prediction using machine learning: analyzing weather conditions, and model performance (Master's thesis, M. Abbas).‏
-Chang, I., Park, H., Hong, E., Lee, J., & Kwon, N. (2022). Predicting effects of built environment on fatal pedestrian accidents at location-specific level: Application of XGBoost and SHAP. Accident Analysis & Prevention, 166, 106545.‏
-Chen, Y., Yuan, R., Wei, J., & Li, S. (2023). Research on the influencing factors of elderly pedestrian traffic accidents considering the built environment. International Review for Spatial Planning and Sustainable Development, 11(1),  44-63.‏ doi:10.1016/j.ssci.2013.08.015
-Dundas, G. (2020, April). Pedestrian suspension bridge for Bibbulmun Track. In Austroads Bridge Conference, 10th, Melbourne, Victoria, Australia fatalities and crashes: a case study of Illinois
county-level data. Accid. Anal. Prev. 36 4, 525–532.
-Hall, J. W., (1983). Pedestrian Accident Accident on Rural Highways. Transportation Research Record, No. 904, 46-50.
Health Concern (2019). An Observational Study From Iranian Population. Traffic Inj. Prev. 16 1, 36–41. doi:10.1080/15389588.2014.898182
-https://amerandish.com.
-https://amerandish.com
-Kamboozia, N., Ameri, M., & Hosseinian, S. M. (2020). Statistical analysis and accident prediction models leading to pedestrian injuries and deaths on rural roads in Iran. International Journal of Injury Control and Safety Promotion, 27(4), 493-509.‏
-Lee, J., Abdel-Aty, M., Cai, Q., Wang, L., & Huang, H. (2018). Integrated modeling approach for non-motorized mode trips and fatal crashes in the framework of transportation safety planning. Transportation Research Record, 2672(32), 49-60.‏
-Meocci, M., Branzi, V., Martini, G., Arrighi, R., & Petrizzo, I. (2021). A predictive pedestrian crash model based on artificial intelligence techniques. Applied Sciences, 11(23), 11364.‏
-Naderan, A., & Safarzadeh, M. (2023). Modeling the risk of urban accidents based on the characteristics of the physical environment. Ministry of Science, Research, and Technology - University of Science and Technology - Faculty of Engineering.
networks and the number of transport fatalities at the city level. Saf. Sci. 62, 114–120. doi:10.1016/j.ssci.2013.08.015
 -Office of Technical Studies and Standards, Ministry of Planning and Budget. (1996). Pedestrian facilities - Technical foundations. Publication No. 1441.
-Olowosegun, A., Babajide, N., Akintola, A., Fountas, G., & Fonzone, A. (2022). Analysis of pedestrian accident injury-severities at road junctions and crossings using an advanced random parameter modelling framework: The case of Scotland. Accident Analysis & Prevention, 169, 106610.‏
-Park, S., & Ko, D. (2020). A multilevel model approach for investigating individual accident characteristics and neighborhood environment characteristics affecting pedestrian-vehicle crashes. International Journal of Environmental Research and Public Health, 17(9), 3107.‏
-Riahi, M., Salehi, M., Mansournia, M.A., (2015). The Road Traffic Crashes as a Neglected Public.
-Tao, W., Aghaabbasi, M., Ali, M., Almaliki, A. H., Zainol, R., Almaliki, A. A., & Hussein, E. E. (2022). An advanced machine learning approach to predicting pedestrian fatality caused by road crashes: A step toward sustainable pedestrian safety. Sustainability, 14(4), 2436.‏Transportation Officials, Washington, D.C.
-Ulak, M. B., Kocatepe, A., Yazici, A., Ozguven, E. E., & Kumar, A. (2021). A stop safety index to address pedestrian safety around bus stops. Safety Science, 133, 105017.‏
-Xie, K., Ozbay, K., & Yang, H. (2015). Spatial analysis of highway incident durations in the context of Hurricane Sandy. Accident Analysis & Prevention, 74, 77-86.‏
-Yue, H. (2024). Investigating the influence of streetscape environmental.
Journal of Transportation Research
Volume 23, Issue 4
Autumn 2026
Pages 535-548