Građevinar, Vol. 77 No. 12., 2025.
Izvorni znanstveni članak
https://doi.org/10.14256/JCE.4319.2025
Predicting unsafe road sections using machine learning
Riste Ristov
Slobodan Ognjenović
Zlatko Zafirovski
Sažetak
This paper presents an ML methodology to predict hazardous road segments, using the weighted accident index (Wi). The analysis covers 161 road segments in North Macedonia (~1,300 km)—with 23+1 variables categorized into Road, Traffic, Environmental, and Accident data. Feature influence is evaluated using six models with an 80/20 training/testing split. Weighted SHAP is applied to obtain a single variable ranking; XGBoost with 15 inputs is the final predictor. The model achieves a validated performance (R² = 0.65), while operational prioritization yields AUROC = 0.69 at Wi ≥ 10.13, enabling timely identification of hazardous segments and interventions by relevant authorities.
Ključne riječi
road safety; machine learning; prediction; SHAP; weighted accident index; traffic analysis
Hrčak ID:
344215
URI
Datum izdavanja:
1.2.2026.
Posjeta: 265 *