基于机器学习的驾驶行为安全风险评估模型的研究

通过信息化系统收集车辆运行轨迹数据,结合工作实际构建安全风险检查指标体系,为克服传统的风险评估模型中评价指标个人主观性强、信息处理效能低的问题。首先,对信息系统采集到的车辆运行数据进行One-Hot编码,然后,利用XGBoost算法建立驾驶行为安全评估模型并对模型参数进行优化提高模型性能和准确度。结果表明,基于XGBoost的驾驶行为安全评估模型可以根据采集到的数据揭示驾驶行为与风险评估等级之间的交互关系,能够反映出更加深层次安全问题,为安全评价和隐患整改提供可靠的依据,使管理人员的决策更具有针对性和前瞻性。

Through the information system to collect vehicle trajectory data,combined with the actual work to build a safety risk inspection index system,in order to overcome the problems of strong personal subjectivity and low efficiency of infbmiation processing in the traditional risk assessment model.First,the driving behavior data collected by the information system is one hot coded;Then,the XGBoost algorithm is used to establish the driving behavior safety evaluation model,and the model parameters are optimized to improve the performance and accuracy of the model.The results show that the driving behavior safety assessment model based on XGBoost can reveal the interactive relationship between driving behavior and risk assessment level according to the collected data,reflect deeper safety problems,provide a reliable basis for safety assessment and hidden danger rectification,and make managers'decisions more targeted and forward-looking.