摘要
针对城市快速路交通事件持续时间影响因素的复杂性和不确定性,结合贝叶斯网络和非参数回归方法,提出了一种新的快速路交通事件持续时间预测模型.采用上海市快速路监控中心数据,经过降噪处理,生成样本数据;在分析样本数据特征基础上,确定了贝叶斯网络的结构学习方法与参数学习方法;对贝叶斯网络模型的结果用非参数回归算法生成持续时间预测值.最后,对模型预测精度进行了验证,发现模型预测效果较好.
According to the complexity and uncertainty of impact fact of traffic event duration on urban expressway, a new forecasting model using Bayesian Network and non- parametric regression for traffic incident duration was proposed. A sample database, provided by Shanghai Expressway Monitoring Center, was generated by noise reduction. The algorisms of structure learning and parameter learning were determined based on data characteristics, and the forecast results with non-parametric regression were obtained. Finally, the forecasting model was tested with new data and the results verified the accuracy of the model.
出处
《同济大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2013年第7期1015-1019,共5页
Journal of Tongji University:Natural Science
基金
国家"八六三"高技术研究发展计划(2011AA110305)
关键词
快速路交通
事件持续时间
贝叶斯网络
非参数
回归
预测模型
expressway
traffic incident duration
BayesianNetwork
non-parametric regression
forecast model
