Enhancing perceived risk prediction of human-vehicle collisions in urban and construction environments by incorporating motion dynamics and behavior-based features

Human-vehicle collisions pose risks in urban and construction environments, necessitating proactive assessment. Most prior studies rely on proximity and time-to-collision (TTC), overlooking behavior-driven factors such as sudden motion changes and instability. Unlike human factors that emphasize key cognitive states, behavior-driven factors cannot directly capture them but infer them through external movement patterns associated with perceived risk. This study proposes a machine learning framework integrating motion-based and behavior-driven features to predict human-perceived collision risk. Perceived risk from 21 participants were collected in virtual urban, factory, and construction settings. Features including proximity, TTC, velocity, velocity change, and entropy were extracted across multiple time windows (0.5–5.0s prior to perceived risk) and analyzed to identify optimal prediction frames. LightGBM achieved 98.00% accuracy for detectingcollision risk presence, while random forest yielded 80.13% for binary risk levels. Performance improved when incorporating features 2–3s before risk, underscoring the predictive value of early behavioral signals. SHAP analysis confirmed proximity and TTC as dominant predictors, but behavior-driven features amplified risk signals in borderline cases. This framework bridges objective risk indicators with human perception, supporting AI-driven safety systems through warnings and intervention timing in autonomous driving, construction safety, and pedestrian risk management, contributing to proactive risk prevention.