文献类型：期刊文献

英文题名：Deep Autoencoder Neural Networks for Short-Term Traffic Congestion Prediction of Transportation Networks

作者：Zhang, Sen Yao, Yong Hu, Jie Zhao, Yong Li, Shaobo Hu, Jianjun

第一作者：Zhang, Sen

通信作者：Li, SB[1];Hu, JJ[1];Hu, JJ[2]

机构：[1]Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu 610041, Sichuan, Peoples R China;[2]Univ Chinese Acad Sci, Beijing 100049, Peoples R China;[3]Guizhou Inst Technol, Sch Big Data, Guiyang 550003, Guizhou, Peoples R China;[4]Guizhou Univ, Sch Mech Engn, Guiyang 550003, Guizhou, Peoples R China;[5]GuiZhou Univ Finance & Econ, Coll Big Data Stat, Guiyang 550025, Guizhou, Peoples R China;[6]Univ South Carolina, Dept Comp Sci & Engn, Columbia, SC 29201 USA

第一机构：Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu 610041, Sichuan, Peoples R China

通信机构：corresponding author), Guizhou Univ, Sch Mech Engn, Guiyang 550003, Guizhou, Peoples R China;corresponding author), Univ South Carolina, Dept Comp Sci & Engn, Columbia, SC 29201 USA.

年份：2019

卷号：19

期号：10

外文期刊名：SENSORS

收录：;EI(收录号：20192607115081);Scopus(收录号：2-s2.0-85066351917);WOS:【SCI-EXPANDED(收录号:WOS:000471014500016)】；

基金：This research was funded by The National Natural Science Foundation of China under Grant No. 91746116 and 51741101, and Science and Technology Project of Guizhou Province under Grant Nos. [2018]5788, Talents [2015]4011 and [2016]5013, Collaborative Innovation [2015]02.

语种：英文

外文关键词：transportation network; traffic congestion forecasting; spatial-temporal correlation; deep learning; end-to-end; deep autoencoder; convolutional neural network; long short-term memory

摘要：Traffic congestion prediction is critical for implementing intelligent transportation systems for improving the efficiency and capacity of transportation networks. However, despite its importance, traffic congestion prediction is severely less investigated compared to traffic flow prediction, which is partially due to the severe lack of large-scale high-quality traffic congestion data and advanced algorithms. This paper proposes an accessible and general workflow to acquire large-scale traffic congestion data and to create traffic congestion datasets based on image analysis. With this workflow we create a dataset named Seattle Area Traffic Congestion Status (SATCS) based on traffic congestion map snapshots from a publicly available online traffic service provider Washington State Department of Transportation. We then propose a deep autoencoder-based neural network model with symmetrical layers for the encoder and the decoder to learn temporal correlations of a transportation network and predicting traffic congestion. Our experimental results on the SATCS dataset show that the proposed DCPN model can efficiently and effectively learn temporal relationships of congestion levels of the transportation network for traffic congestion forecasting. Our method outperforms two other state-of-the-art neural network models in prediction performance, generalization capability, and computation efficiency.