基于KNN-LSTM的短时交通流预测  

Short-term Traffic Flow Prediction Based on KNN-LSTM

作　　者：罗向龙[1,2] 李丹阳 杨彧 张生瑞[2] LUO Xianglong;LI Danyang;YANG Yu;ZHANG Shengrui(School of Information Engineering,Chang'an University,Xi'an 710064,China;College of Highway,Chang'an University,Xi'an 710064,China)

机构地区：[1]长安大学信息工程学院,西安710064 [2]长安大学公路学院,西安710064

出　　处：《北京工业大学学报》2018年第12期1521-1527,共7页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(5157081053);云南省交通运输厅科技计划资助项目(2014(A)29);长安大学研究生科研创新实践项目(2018098)

摘　　要：针对现有预测模型无法在交通大数据中提取交通流序列的内部规律,且未能充分利用交通流的时空相关性以实现高精度预测的问题,提出了一种基于K-最近邻(K-nearest neighbor,KNN)与长短时记忆(long short term memory,LSTM)网络模型相结合的短时交通流预测模型.采用KNN算法选择路网中与预测站点时空相关的检测站,以选择的检测站的交通流序列构造数据集,将其输入LSTM模型中进行训练及测试,并通过美国交通研究数据实验室的真实交通数据对提出的模型进行验证.结果表明:与现有的交通预测模型相比,该方法能更好地提取交通流序列的时空特性,预测准确率平均可提高12. 28%,可为交通诱导与控制提供必要的依据.To solve the problem that existing prediction models cannot extract the internal rules of the traffic flow in traffic big data and fail to make full use of spatiotemporal correlation characteristics to achieve high accurate prediction,a short-term traffic flow prediction model was proposed based on K-nearest neighbor(KNN)and long short term memory(LSTM).The KNN algorithm was used to select the stations that were related to the test station in the road network.The traffic flow data in selected stations were used as the training and testing datasets for the LSTM model.The proposed model was verified by real traffic data from the Transportation Research Data Lab in USA.Results show that the proposed method can better extract the spatiotemporal characteristics of traffic flow sequences,and the prediction accuracy can be improved by 12.28%on average compared with the existing prediction model,which can provide the necessary basis for traffic guidance and control.

关 键 词：智能交通 交通流预测 K-最近邻(KNN) 深度学习 长短时记忆(LSTM)网络 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]