Reliable risk identification based on driver behavior data underpins real-time safety feedback, fleet risk management, and evaluation of driver-assist systems. While naturalistic driving studies have become foundational for providing real-world driver behavior data, the existing frameworks for identifying risk based on such data have two fundamental limitations: (i) they rely on predefined time windows and fixed thresholds to disentangle risky and normal driving behavior, and (ii) they assume behavior is stationary across drivers and time, ignoring heterogeneity and temporal drift. In practice, these limitations can lead to timing errors and miscalibration in alerts, weak generalization to new drivers/routes/conditions, and higher false-alarm and miss rates, undermining driver trust and reducing safety intervention effectiveness. To address this gap, we propose a unified, context-aware framework that adapts labels and models over time and across drivers via rolling windows, joint optimization, dynamic calibration, and model fusion, tailored for time-stamped kinematic data. The framework is tested using two safety indicators, speed-weighted headway and harsh driving events, and three models: Random Forest, XGBoost, and Deep Neural Network (DNN). Speed-weighted headway yielded more stable and context-sensitive classifications than harsh-event counts. XGBoost maintained consistent performance under changing thresholds, whereas DNN achieved higher recall at lower thresholds but with greater variability across trials. The ensemble aggregated signals from multiple models into a single risk decision, balancing responsiveness to risky behavior with control of false alerts. Overall, the framework shows promise for adaptive, context-aware risk detection that can enhance real-time safety feedback and support driver-focused interventions in intelligent transportation systems.

翻译：基于驾驶员行为数据的可靠风险识别是实时安全反馈、车队风险管理以及驾驶辅助系统评估的基础。尽管自然驾驶研究已成为提供真实世界驾驶员行为数据的重要基础，但现有基于此类数据的风险识别框架存在两个根本性局限：(i) 依赖预定义时间窗口和固定阈值来区分危险与正常驾驶行为；(ii) 假设驾驶行为在驾驶员间和跨时间维度保持平稳，忽略了个体异质性和时间漂移。实践中，这些局限可能导致预警时机错误与校准偏差、对新驾驶员/路线/条件的泛化能力弱、以及更高的误报率和漏报率，从而损害驾驶员信任并降低安全干预有效性。为弥补这一缺陷，我们提出一个统一的上下文感知框架，通过滚动窗口、联合优化、动态校准和模型融合技术，实现标签与模型在时间和驾驶员维度上的自适应调整，专门适用于时间戳运动学数据。该框架使用两个安全指标（速度加权车头时距和急骤驾驶事件）和三种模型（随机森林、XGBoost和深度神经网络）进行验证。实验表明，速度加权车头时距比急骤事件计数能产生更稳定且对上下文敏感的分类结果。XGBoost在阈值变化时保持稳定性能，而深度神经网络在较低阈值下获得更高召回率但跨试验变异性较大。集成模型将多模型信号聚合为单一风险决策，在风险行为响应与误报控制间取得平衡。总体而言，该框架展现了自适应上下文感知风险检测的潜力，可提升智能交通系统中实时安全反馈的效能，并为面向驾驶员的干预措施提供支持。