A Multi-Stream Feature Fusion Approach for Traffic Prediction
Zhishuai Li1; Gang Xiong1; Yonglin Tian1; Yisheng Lv1; Yuanyuan Chen1; Pan Hui2; Xiang Su3
Source PublicationIEEE Transactions on Intelligent Transportation Systems
2020
Volume99Issue:1Pages:1-10
Abstract

Accurate and timely traffic flow prediction is crucial for intelligent transportation systems (ITS). Recent advances in graph-based neural networks have achieved promising prediction results. However, some challenges remain, especially regarding graph construction and the time complexity of models. In this paper, we propose a multi-stream feature fusion approach to extract and integrate rich features from traffic data and leverage a data-driven adjacent matrix instead of the distance-based matrix to construct graphs. We calculate the Spearman rank correlation coefficient between monitor stations to obtain the initial adjacent matrix and fine-tune it while training. As to the model, we construct a multi-stream feature fusion block (MFFB) module, which includes a three-channel network and the soft-attention mechanism. The three-channel networks are graph convolutional neural network (GCN), gated recurrent unit (GRU) and fully connected neural network (FNN), which are used to extract spatial, temporal and other features, respectively. The soft-attention mechanism is utilized to integrate the obtained features. The MFFB modules are stacked, and a fully connected layer and a convolutional layer are used to make predictions. We conduct experiments on two real-world traffic prediction tasks and verify that our proposed approach outperforms the state-of-the-art methods within an acceptable time complexity.

KeywordTraffic prediction, graph convolutional neural network, deep learning, multi-stream
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/40596
Collection复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
Corresponding AuthorYisheng Lv
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.The Hong Kong University of Science and Technology
3.University of Helsinki
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhishuai Li,Gang Xiong,Yonglin Tian,et al. A Multi-Stream Feature Fusion Approach for Traffic Prediction[J]. IEEE Transactions on Intelligent Transportation Systems,2020,99(1):1-10.
APA Zhishuai Li.,Gang Xiong.,Yonglin Tian.,Yisheng Lv.,Yuanyuan Chen.,...&Xiang Su.(2020).A Multi-Stream Feature Fusion Approach for Traffic Prediction.IEEE Transactions on Intelligent Transportation Systems,99(1),1-10.
MLA Zhishuai Li,et al."A Multi-Stream Feature Fusion Approach for Traffic Prediction".IEEE Transactions on Intelligent Transportation Systems 99.1(2020):1-10.
Files in This Item: Download All
File Name/Size DocType Version Access License
2020 TITS_Zhishuai.p(3572KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhishuai Li]'s Articles
[Gang Xiong]'s Articles
[Yonglin Tian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhishuai Li]'s Articles
[Gang Xiong]'s Articles
[Yonglin Tian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhishuai Li]'s Articles
[Gang Xiong]'s Articles
[Yonglin Tian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2020 TITS_Zhishuai.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.