Integrated Risk Assessment of Road Traffic Accident Clusters Based on Weighted Casualty Metrics
DOI:
https://doi.org/10.31861/sisiot2026.1.01013Keywords:
road traffic accident, accident cluster, integrated risk assessment, clustering, road safetyAbstract
The paper addresses the problem of identifying and prioritizing hazardous road traffic accident concentration areas based on accident frequency and casualty severity. The relevance of the study is motivated by the increasing number of accidents with injuries and fatalities, as well as the limitations of approaches based solely on quantitative indicators without considering the severity of consequences. Under such conditions, treating accidents of different severity levels equally leads to distorted assessments of road safety and reduces the effectiveness of decision-making in traffic safety management. The study proposes an integrated risk assessment method based on weighted coefficients assigned to different categories of casualties. Minor injuries are assigned 1-point, severe injuries – 3 points, and fatalities – 9 points. Based on these coefficients, a generalized risk indicator is formed for both individual accidents and their aggregation within spatial clusters. The proposed approach is integrated into the process of clustering road traffic accidents using geographic coordinates and distance-based metrics. This allows not only the identification of accident concentration areas but also their ranking according to the level of danger. As a result, it becomes possible to detect critical locations, including those with a relatively low number of accidents but high severity of consequences. The practical implementation of the method is carried out within an information system for accident analysis, providing automated data processing, clustering, and report generation. The proposed method enables accident clusters to be ranked using both accident frequency and the severity-weighted consequences of the recorded accidents. The method was evaluated using accident records from 2017 to 2025 for the Ivano-Frankivsk urban territorial community, with a spatial threshold of 50m and a minimum cluster size of three accidents. The results show that casualty-weighted ranking differs from ranking based solely on accident frequency: clusters with fewer accidents but more fatalities and severe injuries may receive a higher priority. From the perspective of infocommunication systems, the proposed method can be used as an analytical component of an integrated road safety monitoring platform that combines distributed data acquisition, communication, centralized processing, and geospatial visualization. The system architecture also provides a basis for further integration with IoT-enabled traffic and road infrastructure devices.
Downloads
References
A. Ziakopoulos and G. Yannis, “A review of spatial approaches in road safety,” Accident Analysis & Prevention, vol. 135, Art. no. 105323, 2020. doi: 10.1016/j.aap.2019.105323.
Z. Xie and J. Yan, “Kernel density estimation of traffic accidents in a network space,” Computers, Environment and Urban Systems, vol. 32, no. 5, pp. 396–406, 2008. doi: 10.1016/j.compenvurbsys.2008.05.001.
T. K. Anderson, “Kernel density estimation and K-means clustering to profile road accident hotspots,” Accident Analysis & Prevention, vol. 41, no. 3, pp. 359–364, 2009. doi: 10.1016/j.aap.2008.12.014.
S. Erdogan, I. Yilmaz, T. Baybura, and M. Gullu, “Geographical information systems aided traffic accident analysis system case study: City of Afyonkarahisar,” Accident Analysis & Prevention, vol. 40, no. 1, pp. 174–181, 2008. doi: 10.1016/j.aap.2007.05.004.
E. S. M. M. Zahran, S. J. Tan, E. H. A. Tan, N. A. A. B. M. ’Asri Putra, Y. H. Yap, and E. K. Abdul Rahman, “Spatial analysis of road traffic accident hotspots: Evaluation and validation of recent approaches using road safety audit,” Journal of Transportation Safety & Security, vol. 13, no. 6, pp. 575–604, 2021. doi: 10.1080/19439962.2019.1658673.
M. R. Islam, I. J. Jenny, M. Nayon, M. R. Islam, M. Amiruzzaman, and M. Abdullah-Al-Wadud, “Clustering algorithms to analyze the road traffic crashes,” in Proc. 2021 International Conference on Science & Contemporary Technologies (ICSCT), 2021, pp. 1–6. doi: 10.1109/ICSCT53883.2021.9642542.
M. S. Alam and N. J. Tabassum, “Spatial pattern identification and crash severity analysis of road traffic crash hot spots in Ohio,” Heliyon, vol. 9, no. 5, Art. no. e16303, 2023. doi: 10.1016/j.heliyon.2023.e16303.
W. T. Gedamu, U. Plank-Wiedenbeck, and B. T. Wodajo, “A spatial autocorrelation analysis of road traffic crash by severity using Moran’s I spatial statistics: A comparative study of Addis Ababa and Berlin cities,” Accident Analysis & Prevention, vol. 200, Art. no. 107535, 2024. doi: 10.1016/j.aap.2024.107535.
A. Mesic, J. Damsere-Derry, C. Feldacker, S. J. Mooney, A. Gyedu, C. Mock, A. Kitali, B. H. Wagenaar, et al., “Identifying emerging hot spots of road traffic injury severity using spatiotemporal methods: Longitudinal analyses on major roads in Ghana from 2005 to 2020,” BMC Public Health, vol. 24, Art. no. 1609, 2024. doi: 10.1186/s12889-024-18915-x.
S. Mohammed, A. H. Alkhereibi, A. Abulibdeh, R. N. Jawarneh, and P. Balakrishnan, “GIS-based spatiotemporal analysis for road traffic crashes: In support of sustainable transportation planning,” Transportation Research Interdisciplinary Perspectives, vol. 20, Art. no. 100836, 2023. doi: 10.1016/j.trip.2023.100836.
Y. Berhanu, D. Schröder, B. T. Wodajo, and E. Alemayehu, “Machine learning for predictions of road traffic accidents and spatial network analysis for safe routing on accident and congestion-prone road networks,” Results in Engineering, vol. 23, Art. no. 102737, 2024. doi: 10.1016/j.rineng.2024.102737.
M. Tahir, Y. Qiao, N. Kanwal, B. Lee, and M. N. Asghar, “Real-time event-driven road traffic monitoring system using CCTV video analytics,” IEEE Access, vol. 11, pp. 139097–139111, 2023. doi: 10.1109/ACCESS.2023.3340144.
D. K. Endashaw, K. A. Habtegiorgis, B. M. Al-Ramadan, H. M. Al-Ahmadi, and B. F. Deressa, “A systematic review on GIS-based road traffic accidents analysis and road safety audit,” Computational Urban Science, vol. 5, Art. no. 53, 2025. doi: 10.1007/s43762-025-00221-w.
B. Pashkovskyi and M. Slabinoha, “Automation of determination of areas and places of concentration of traffic accidents at the Ivano-Frankivsk urban territorial community using geocoding,” International Science Journal of Engineering & Agriculture, vol. 2, no. 4, pp. 9–18, 2023. doi: 10.46299/j.isjea.20230204.02.
B. V. Pashkovskyi and M. I. Slabinoha, “Improvement of the automated process for identifying road traffic accident concentration areas and locations in the Ivano-Frankivsk urban territorial community,” Bulletin of Kherson National Technical University, no. 2(89), pp. 204–210, 2024. doi: 10.35546/kntu2078-4481.2024.2.29.
B. V. Pashkovskyi, “Automated process for identifying road traffic accident concentration areas and locations in the Ivano-Frankivsk urban territorial community,” Bulletin of Kherson National Technical University, no. 2(93), pp. 288–292, 2025. doi: 10.35546/kntu2078-4481.2025.2.2.34.
Published
Issue
Section
License
Copyright (c) 2026 Security of Infocommunication Systems and Internet of Things
This work is licensed under a Creative Commons Attribution 4.0 International License.
