摘要
交通速度预测在智能交通系统中起着重要的作用,准确、快速的交通速度预测有利于及时掌握城市道路交通状况,能够有效实行交通诱导。针对交通速度具有极强的周期性,在工作日和非工作日之间存在较大差异,导致预测精度不高的问题,分别选取公开的工作日和非工作日交通速度数据,构建基于长短期记忆神经网络的城市交通速度预测模型。实验验证采用广州市20条路段的交通数据,结果表明,区分工作日和非工作日的平均绝对百分比误差、平均绝对误差和均方根误差的平均值比不区分均要小,说明区分工作日和非工作日可以有效地提高交通速度的预测精度。
Traffic speed prediction plays an important role in Intelligent Transportation System(ITS). Accurate and fast traffic speed prediction is conducive to timely grasp the urban road traffic conditions and can effectively implement traffic guidance. Traffic speed has a strong periodicity and a big difference between workdays and non-workdays, which leads to a low prediction accuracy. In order to solve the problem, an urban traffic speed prediction model based on long short-term memory neural network is constructed according to public traffic speed data of workdays and non-workdays. The experimental verification uses traffic data of 20 roads of Guangzhou city, and the results show that the average values of mean absolute percentage error, mean absolute error and root mean square error of distinguishing workdays and non-workdays are smaller than those of not distinguishing between workdays and non-workdays, indicating that this strategy can effectively improve the effect of traffic speed prediction accuracy.
作者
吕开云
邱万锦
龚循强
支君豪
汪宏宇
LYU Kaiyun;QIU Wanjin;GONG Xunqiang;ZHI Junhao;WANG Hongyu(School of Geomatics,East China University of Technology,Nanchang 330013,China;Key Laboratory of Marine Environmental Survey Technology and Application,Ministry of Natural Resources,Guangzhou 510310,China;Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake,Ministry of Natural Resources,East China University of Technology,Nanchang 330013,China)
出处
《东华理工大学学报（自然科学版）》
CAS
2023年第1期77-84,共8页
Journal of East China University of Technology(Natural Science)
基金
自然资源部海洋环境探测技术与应用重点实验室开放基金项目(MESTA-2021-B001)
国家自然科学基金项目(42101457)
江西省教育厅科学技术科技项目(GJJ150591)
东华理工大学放射性地质与勘探技术国防重点学科实验室开放基金项目(REGT1219)。
关键词
智能交通
交通速度预测
长短期记忆神经网络
周期性
intelligent transportations
traffic speed prediction
long short-term memory neural network
periodicity
