Aiming at the phenomenon that the traffic flow information of each section of the express-
way is quite different, in order to improve the accuracy of traffic flow prediction, the attention mecha-
nism was introduced into convolutional neural networks, and a multi-kernel adaptive network
(MKAN) was designed to model the temporal-spatial relations among traffic flow data. First, multi-
branch convolution was performed on the input historical traffic flow data, and the traffic flow charac-
teristic of different scales was obtained. Then, the weight of each convolution branch was self-adap-
tively adjusted according to the input information, the multi-channel feature maps of each branch were
weighted and summed. Finally, according to the fusion feature maps, the multi-layer perceptron was
used to predict the traffic flow in the next period. To carry out model verification and comparative
analysis, the experiment was designed based on highway traffic flow data from California Department
of Transportation (Caltrans) Performance Measurement System (PeMS). The experiment results
showed that at most sites, the prediction root mean square error and the mean absolute error of MKAN
were lower than that of long short-term memory network, gated recurrent unit, K-nearest neighbor al-
gorithm and support vector regression model. Conducting whole-day traffic flow prediction for site
No.140, the absolute prediction error of MKAN was smaller than other comparison models at each
time of the day. Compared with single-kernel convolutional neural networks, the prediction root mean
square error and the mean absolute error of MKAN were reduced by more than 7% at most sites. Con-
ducting whole-day traffic flow prediction for site No.31, the absolute prediction error of MKAN was
smaller than single-kernel convolutional neural networks at most time of the day. Experiments have
proved that MKAN can effectively improve the accuracy of traffic flow prediction and its prediction
effect is better than some traditional prediction methods and si
习金浩 ，孟峰 ，朱凤华 ，贺正冰 ，李润梅 ，吕宜生
. Highway Traffic Flow Prediction Method Based on
Multi-Kernel Adaptive Network[J]. Transport Research, 2021
, 7(4)
: 1
-9
.
DOI: 10.16503/j.cnki.2095-9931.2021.04.001
[1] 王雪菲，丁维龙. 面向高速公路大数据的短时流量预测方法[J]. 计算机应用，2019，39（1）：87-92.
[2] 梁轲，谭建军，李英远. 一种基于MapReduce的短时交通流预测方法[J]. 计算机工程，2015，41（1）：174-179.
[3] 吴晋武，张海峰，冉旭东. 基于数据约减和支持向量机的非参数回归短时交通流预测算法[J]. 公路交通科技，2020，37（7）：129-134.
[4] 宗春光，宋靖雁，任江涛，等. 基于相空间重构的短时交通流预测研究[J]. 公路交通科技，2003，20（4）：71-75.
[5] 高勇，陈锋. 基于小波分析的短时交通流非参数回归预测[J]. 中国科学技术大学学报，2008，38（12）：1427-1431.
[6] 史其信，郑为中. 道路网短期交通流预测方法比较[J]. 交通运输工程学报，2004，4（4）：68-71，83.
[7] 高慧，赵建玉，贾磊. 短时交通流预测方法综述[J]. 济南大学学报（自然科学版），2008，22（1）：88-94.
[8] HUANG W H, SONG G J, HONG H K, et al. Deep architecture for traffic flow prediction: Deep belief networks with multitask learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(5): 2191-2201.
[9] Lü Y S, DUAN Y J, KANG W W, et al. Traffic flow prediction with big data: A deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 865-873.
[10] YANG H F, DILLON T S, CHEN Y P P. Optimized structure of the traffic flow forecasting model with a deep learning approach[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2371-2381.
[11] FU R, ZHANG Z, LI L. Using LSTM and GRU neural network methods for traffic flow prediction[C]// 2016 31st Youth Academic Annual Conference of Chinese Association of Automation. Wuhan: IEEE, 2016: 324-328.
[12] WEI W Y, WU H H, MA H D. An AutoEncoder and LSTM-based traffic flow prediction method[J]. Sensors(Basel), 2019, 19(13): 2946-2961.
[13] DAI G W, MA C X, XU X C. Short-term traffic flow prediction method for urban road sections based on space-time analysis and GRU[J]. IEEE Access, 2019, 7: 143025-143035.
[14] YANG B L, SUN S L, LI J Y, et al. Traffic flow prediction using LSTM with feature enhancement[J]. Neurocomputing, 2019, 332: 320-327.
[15] 罗文慧，董宝田，王泽胜．基于CNN-SVR混合深度学习模型的短时交通流预测[J]．交通运输系统工程与信息，2017，17（5）：68-74．
[16] ZHANG W B, YU Y H, QI Y, et al. Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning[J]. Transportmetrica A: Transport Science, 2019, 15(2): 1688-1711.
[17] DENG S J, JIA S Y, CHEN J. Exploring spatial-temporal relations via deep convolutional neural networks for traffic flow prediction with incomplete data[J]. Applied Soft Computing, 2019, 78: 712-721.
[18] LI X, WANG W H, HU X L, et al. Selective Kernel Networks[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 510-519.
