摘要
城市交通流量通常较大,路网交通预测时数据繁复、特征参数较多,导致预测速率与精度较低。为此,提出基于多维数据挖掘的城市路网多尺度交通流预测方法。采用数据清洗方式对数据预处理,根据道路交通变化情况确定交通流特征参数;利用傅里叶变换、卷积算法挖掘交通流时空特征,运用注意力函数、权重矩阵挖掘交通流时间特征;通过时空相关性与图的拓扑结构特性建立交通流预测模型,获取下一时刻道路交通变化情况,完成交通流预测。实验结果表明,该方法能够有效预测道路交通每个时段流量状态,预测精度始终高于97%,15 s内就能完成8个路段交通流的预测。
The urban traffic flow is usually large,data is complicated and there are many characteristic parameters in road network traffic prediction,resulting in low prediction speed and accuracy.Therefore,a multi-scale traffic flow prediction method of urban road network based on multi-dimensional data mining is proposed.The data are preprocessed by data cleaning method,and the characteristic parameters of traffic flow are determined according to the changes of road traffic.Fourier transform and convolution algorithm are used to excavate the spatial-temporal characteristics of traffic flow,attention function and weight matrix are used to excavate the temporal characteristics of traffic flow.The traffic flow prediction model is established by the spatial-temporal correlation and the topological structure characteristics of the graph to obtain the road traffic change in the next moment and complete the traffic flow prediction.The experimental results show that this method can effectively predict the traffic flow state of each period of road traffic,and the prediction accuracy is always higher than 97%,and the traffic flow prediction of 8 road sections can be completed within 15 s.
作者
吕庆礼
LÜQingli(Nanjing Yangtze River Urban Architectural Design Co.,Ltd.,Nanjing 210022,China)
出处
《微型电脑应用》
2024年第11期289-293,共5页
Microcomputer Applications
关键词
多维数据挖掘
城市路网
交通流
时空特征
multi-dimensional data mining
urban road network
traffic flow
spatial-temporal characteristics
作者简介
吕庆礼(1978-),男,硕士,高级工程师,研究方向为交通规划、交通设计、道路工程设计。
