Identification of Road Black Spots Based on the Sliding Window Optimization and Safety Performance Function Development




black spots, density-based spatial clustering, network screening, optimization, sliding window, safety performance function


The sliding window method is a road network screening approach commonly used for identifying black spots. Previous studies have indicated that the selection of window length significantly impacts the black spot identification process. This research proposes a new method that optimizes the sliding window framework by examining its characteristics. The optimization methodology employed in this study is as follows: Firstly, the road is segmented, and for each segment, different scenarios of window lengths are chosen using the Density-Based Spatial Clustering of Applications with Noise algorithm. Next, a Safety Performance Function is developed to calculate the predicted and expected number of crashes, as well as the Potential Safety Improvement, for each window movement across all selected scenarios within the segment. Subsequently, the average differences are calculated using the analysis of variance, and the window length with the lowest dispersion of difference values from the mean is identified as the optimal length for each segment. The case study yielded noteworthy results, indicating that the utilization of the sliding window with optimal lengths led to the identification of 122 high-risk black spot-candidates. These points exhibit a higher crash density, effective length, and greater value in quantitative evaluation tests compared to the results obtained using windows with common fixed lengths.


Al-Omari, M., Abdel-Aty, M., & Cai, Q. (2021). Crash analysis and development of safety performance functions for Florida roads in the framework of the context classification system. Journal of Safety Research, 79, 1–13.

Baig, S., Iqbal, W., Berral, J.L., & Carrera, D. (2020). Adaptive sliding windows for improved estimation of data center resource utilization. Future Generation Computer Systems, 104, 212–224.

Bonera, M., Barabino, B., & Maternini, G. (2022). A straightforward framework for road network screening to Lombardy region. Sustainability, 14(19), Article 12424.

Cafiso, S., D’Agostino, C., & Persaud, B. (2018). Investigating the influence of segmentation in estimating safety performance functions for roadway sections. Journal of Traffic and Transportation Engineering, 5(2), 129–136.

Deng, D. (2020). DBSCAN clustering algorithm based on density. 7th International Forum on Electrical Engineering and Automation (IFEEA), Hefei, China, 949–953.

El Bahi, H., & Zatni, A. (2018). Document text detection in video frames acquired by a smartphone based on line segment detector and DBSCAN clustering. Journal of Engineering Science and Technology, 13(2).

Elvik, R. (2007). State-of-the-art approaches to road accident black spot management and safety analysis of road networks. European Commission, National Research Council of Norway, and Institute of Transport Economics.ØI%20rapporter/2007/883-2007/883-2007-nett.pdf

Elvik, R. (2008a). Comparative analysis of techniques for identifying hazardous road locations. Transportation Research Record: Journal of the Transportation Research Board, 2083(1), 72–75.

Elvik, R. (2008b). A survey of operational definitions of hazardous road locations in some European countries. Accident Analysis & Prevention, 40(6), 1830–1835.

Ester, M., Kriegel, H., Sander, J., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 226–231.

Farid, A., Abdel-Aty, M., & Lee, J. (2018). Transferring and calibrating safety performance functions among multiple states. Accident Analysis & Prevention, 117, 276–287.

Farid, A., Abdel-Aty, M. & Lee, J. (2019). Comparative analysis of multiple techniques for developing and transferring safety performance functions. Accident Analysis & Prevention, 122, 85–98.

Fisher, R.A. (1992). Statistical methods for research workers. In S. Kotz, & N.L. Johnson (Eds.), Breakthroughs in Statistics. Springer Series in Statistics. Springer-Verlag, New York, Inc.

Ghadi, M., & Török, Á. (2019a). A comparative analysis of black spot identification methods and road accident segmentation methods. Accident Analysis & Prevention, 128, 1–7.

Ghadi, M., & Török, Á. (2019b). Comparison of different road segmentation methods. Promet – Traffic and Transportation, 31(2), 163–172.

Ghadi, M. (2020). Methods of segmenting and analyzing of road accident data [Doctoral dissertation, Budapest University of Technology and Economics].

Green, E. R. (2018). Segmentation strategies for road safety analysis [Doctoral dissertations, University of Kentucky]. https://uknowledge.uky.Edu/ce_etds/62

HSM. (2010). Highway safety manual (1st ed.). American Association of State Highway and Transportation Officials, Washington, DC.

Kolody, K., Perez-Bravo, D., Zhao, J., & Neuman, T.R. (2022). Highway safety manual user guide. Transportation Research Board (NCHRP Project 17-50).

Kwon, O., Park, M., Yeo, H., & Chung, K. (2013). Evaluating the performance of network screening methods for detecting high collision concentration locations on highways. Accident Analysis & Prevention, 51, 141–149.

Lee, J., Chung, K., Papakonstantinou, I., Kang, S., & Kim, D. (2020). An optimal network screening method of hotspot identification for highway crashes with dynamic site length. Accident Analysis & Prevention, 135, Article 105358.

Lord, D., & Mannering, F. (2010). The statistical analysis of crash-frequency data: a review and assessment of methodological alternatives. Transportation Research Part A: Policy and Practice, 44(5), 291–305.

Medury, A., & Grembek, O. (2016). Dynamic programming-based hot spot identification approach for pedestrian crashes. Accident Analysis & Prevention, 93, 198–206.

Srinivasan, R., & Bauer, K. (2013). Safety performance function development guide: developing jurisdiction specific SPFs. The University of North Carolina Highway Safety Research Center (Report FHWA-SA-14-005).

Szénási, S. (2016). Variable sized planar sliding window technique for searching accident hot spots. 16th International Multidisciplinary Scientific GeoConference SGEM2016, Bulgaria.

Veeramisti, N., Paz, A., & Baker, J. (2020). A framework for corridor-level traffic safety network screening and its implementation using Business Intelligence. Safety Science, 121, 100–110.

Wali, B., Khattak, A., Waters, J., Chimba, D., & Li, X. (2018). Development of safety performance functions: Incorporating unobserved heterogeneityand functional form analysis. Transportation Research Record: Journal of the Transportation Research Board, 2672(30), 9–20.

Zhang, D., Peijie, W., & Xianghai, M. (2018). The optimal sliding window length and increment length for identifying hazardous road segments. Transportation Research Board 97th Annual Meeting, Washington, DC, USA.




How to Cite

Shabani, S., Ayoubinejad, J., & Rahmanian, N. B. (2024). Identification of Road Black Spots Based on the Sliding Window Optimization and Safety Performance Function Development. The Baltic Journal of Road and Bridge Engineering, 19(1), 88-113.