摘要
首先介绍了基于精确传感网络的智能交通系统(ITS)相对于传统交通流传感器网络的优势;然后基于组合预测理论对这类网络的基本交通流模型进行了研究,在模型中引入了更加精确的交通流物理量,包括旅行时间、路段上游及下游的分类交通流量等变量,使所建立模型的可解释信息量更加丰富和易懂,该模型算法为动态算法。交通实测数据实验证明模型的拟合精度较高,拟合值与真值的平均绝对误差值控制在9 s以内,平均相对误差值控制在5%以内,综合各个时段来看,预测的准确度都在90%以上。最后总结了基于精确传感器网络的智能交通系统在实际交通应用中的重大价值。
The advantage of precise sensor network compared to the traditional sensor network was introduced firstly.Then the traffic flow model of precise sensor network was built.To improve the interpretability of the model,the precise license plate identification data were used,and the variables such as the space travel time and the classified traffic flow were introduced.The established model was dynamic in essence.The experimental results show that the fitting accuracy is higher and the mean absolute error between fitted and standard value is less than 9 seconds,and the mean relative error is less than 5%.The model has a high degree of accuracy above 90%.Finally,the great value of precise sensor network in real traffic environment was summarized.
出处
《计算机应用》
CSCD
北大核心
2012年第4期905-909,912,共6页
journal of Computer Applications
基金
国家863计划项目(2008AA01Z208
2009AA01Z405)
国家自然科学基金资助项目(60772150)
四川省应用基础研究资助项目(2010JY0013)
关键词
精确传感网络
智能交通系统
旅行时间
分类交通流量
交通流模型
precise sensor network
Intellignet Transport System（ITS）
travel time
classified traffic flow
traffic flow model
