@article{Qin2026, 
author = {Yaqin Qin and Jiachen Ren and Siyu Wu and Yuan Wang and Yunxin Huang and Hanyu Zhang and Xuanwen Li and Yueran Wang and Jiming Xie},
title = {Human-inspired analysis of influencing factors and coordination mechanisms in highway emergency resource allocation: Insights from Yunnan Province},
year = {2026},
journal = {Journal of Intelligent Construction},
volume = {4},
number = {1},
pages = {9180107},
keywords = {random forest, highway emergency events, emergency personnel allocation, Shapley additive explanations theory, partial dependence plot},
url = {https://www.sciopen.com/article/10.26599/JIC.2026.9180107},
doi = {10.26599/JIC.2026.9180107},
abstract = {With the rapid expansion of highway infrastructure, effective emergency management has emerged as a critical challenge for public transportation safety. Existing resource allocation methodologies are often inadequate for addressing highway incidents, particularly in mountainous regions characterized by complex geological conditions, dynamic weather patterns, and extensive bridge and tunnel networks. This study aims to investigate the intricate relationship between highway emergencies and personnel allocation by systematically identifying the key factors influencing resource distribution. Employing a sophisticated methodological approach, this study integrates the random forest (RF) model with cost management principles to comprehensively assess the significance of various influencing factors. The Shapley additive explanations (SHAP) theory is leveraged to quantify the nuanced contributions of individual factors to emergency staffing, thereby enhancing the interpretability of the model. Through one- and two-dimensional partial dependency plots, we conducted a detailed analysis of the correlations among the critical determinants. The research findings revealed macro-level traffic dynamics and established meaningful connections between specific emergency scenarios and targeted response strategies. By providing localized decision-making insights, this study establishes a robust analytical framework that bridges highway incident characteristics with coordinated emergency responses. Finally, we propose a comprehensive framework that offers high predictive accuracy, logical transparency, and practical adaptability in the highway emergency resource allocation.}
}