research-article

Traffic Flow Prediction Based on Self-attention Mechanism and Deep Packet Residual Network

Authors:

Xuebin Jia,

Tong Li,

Rui Zhu,

Zhan Wang,

Zehui Zhang,

Jiawei WangAuthors Info & Claims

ICIT '19: Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City

Pages 575 - 580

https://doi.org/10.1145/3377170.3377257

Published: 20 March 2020 Publication History

Get Access

Abstract

Traffic flow forecasting is an important function of a traffic information system. In recent years, it has become a research hotspot of experts and scholars in the field of transportation. The traffic flow is affected by spatiotemporal factors, so the traffic flow data is highly nonlinear and complex, which makes the flow data difficult to predict accurately. Therefore, the previous traffic prediction model does not have accuracy and reliability. Under the circumstances, this paper proposes a self-attention mechanism-based packet residual network model (SA-Res2Net) to predict urban traffic flow. Firstly, the internal pixel connection and global correlation of the New York bike data is enhanced through the Self-Attention mechanism. Then, the Attention Map is input into the Res2Net model and divided into 8 channels of in and out traffic data to extract the spatiotemporal correlation of traffic flow with finer-grained multi-scale features. The experimental results show that compared with other traditional models, the model in this paper is of satisfactory predictive value.

References

[1]

Lv Y, Duan Y, Kang W, et al. Traffic flow prediction with big data: a deep learning approach [J]. IEEE Transactions on Intelligent Transportation Systems (S1524--9050), 2015, 16(2): 865--873.

Google Scholar

[2]

Zhang N, Chen H, Chen X, et al. Forecasting Public Transit Use by Crowdsensing and Semantic Trajectory Mining: Case Studies[J]. ISPRS International Journal of Geo-Information, 2016, 5(10):180.

Crossref

Google Scholar

[3]

Rasmussen T K, Ingvardson J B, Nielsen O A. Improved methods to deduct trip legs and mode from travel surveys using wearable GPS devices: A case study from the Greater Copenhagen area[J]. Computers Environment & Urban Systems, 2015, 54:301--313.

Crossref

Google Scholar

[4]

Ashbrook D, Starner T. Using GPS to learn significant locations and predict movement across multiple users[J]. Personal & Ubiquitous Computing, 2003, 7(5):275--286.

Digital Library

Google Scholar

[5]

Wen H, Zhongwei H U, Guo J, et al. Operational Analysis on Beijing Road Network during the Olympic Games[J]. Journal of Transportation Systems Engineering & Information Technology, 2008, 8(6):32--37.

Crossref

Google Scholar

[6]

Gang Yang, Le Wang, Lizhen Dai, et al. Traffic Flow Prediction Based on Adaptive Particle Swarm Optimization of Least Square Support Vector Machine [J]. Control Engineering of China, 2017, 24(9): 1838--1843.

Google Scholar

[7]

Yisheng Lv, Yanjie Duan, Wenwen Kang, etc. Traffic Flow Prediction With Big Data: A Deep Learning Approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 865--873.

Digital Library

Google Scholar

[8]

Yao zhisheng, Shao Chunfu, Gao Yongliang. Research on short-time prediction method of traffic state based on support vector regression machine [J]. Journal of Beijing jiaotong university, 2006, 30(3): 19-22.Y.C.

Google Scholar

[9]

Wang Jin, Shi Qixin. Summary of short-term traffic flow prediction models [J]. China public safety: academic volume, 2005, 1(1): 10--13.

Google Scholar

[10]

Luo xianglong, jiao qinqin, niu liyao, et al. Short-term traffic flow prediction based on deep learning [J].Computer application research, 2017, 34(1): 91--93

Google Scholar

[11]

Wang Jian, Deng Wei, Zhao Jinbao. Short-term traffic flow prediction based on multi-method combination of bayesian networks [J]. Journal of transportation systems engineering and information, 2011, 11(4):147--153.

Google Scholar

[12]

Kong Fanyu, Zhou Yufeng, Chen Gang. Traffic flow prediction method based on spatio-temporal feature mining [J]. Journal of Frontiers of Computer Science, 2019, 46 (7).

Google Scholar

[13]

Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)?-Arguments against avoiding RMSE in the literature[J]. Geoscientific model development, 2014, 7(3): 1247--1250.

Google Scholar

Cited By

View all

Chen YHuang JXu HGuo JSu L(2023)Road traffic flow prediction based on dynamic spatiotemporal graph attention networkScientific Reports10.1038/s41598-023-41932-613:1Online publication date: 7-Sep-2023
https://doi.org/10.1038/s41598-023-41932-6
Bharti SSaini VKumar RVijayvargiya A(2022)Attention Mechanism in Deep Learning for Wind Power Forecasting2022 IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES)10.1109/PEDES56012.2022.10080136(1-6)Online publication date: 14-Dec-2022
https://doi.org/10.1109/PEDES56012.2022.10080136
Wang QYuan YZhang QYang X(2022)Signalized arterial origin-destination flow estimation using flawed vehicle trajectories: A self-supervised learning approach without ground truthTransportation Research Part C: Emerging Technologies10.1016/j.trc.2022.103917145(103917)Online publication date: Dec-2022
https://doi.org/10.1016/j.trc.2022.103917
Show More Cited By

Index Terms

Traffic Flow Prediction Based on Self-attention Mechanism and Deep Packet Residual Network
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Neural networks

Recommendations

Traffic flow matrix-based graph neural network with attention mechanism for traffic flow prediction
Abstract
Traffic flow forecasting is of great importance in intelligent transportation systems for congestion mitigation and intelligent traffic management. Most of the existing methods depend on deep learning to extract the spatial–temporal correlation ...
Graphical abstract

Display Omitted
Highlights
- Traffic flow matrix can bring improvements to the graph neural network for traffic forecasting.
- The designed graph neural network can predict the traffic flow more accurately.
- Introducing the Transformer Encoder to the designed ...
Multi-scale Spatio-temporal Attention Network for Traffic Flow Prediction
Advanced Intelligent Computing Technology and Applications
Abstract
Traffic flow prediction has important implications for multiple fields, such as urban planning, traffic management and transportation. Accurate Traffic flow prediction helps improve transportation efficiency. At the same time, getting accurate ...
A grey convolutional neural network model for traffic flow prediction under traffic accidents
Abstract
Accurate traffic flow prediction can effectively improve traffic efficiency and safety. This has become a trending topic in intelligent transportation systems. However, the occurrence of traffic accidents will cause great fluctuations ...

Comments

Information & Contributors

Information

Published In

ICIT '19: Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City

December 2019

601 pages

ISBN:9781450376631

DOI:10.1145/3377170

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Shanghai Jiao Tong University: Shanghai Jiao Tong University
The Hong Kong Polytechnic: The Hong Kong Polytechnic University
University of Malaya: University of Malaya

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 March 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICIT 2019

ICIT 2019: IoT and Smart City

December 20 - 23, 2019

Shanghai, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
132
Total Downloads

Downloads (Last 12 months)5
Downloads (Last 6 weeks)0

Reflects downloads up to 16 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Chen YHuang JXu HGuo JSu L(2023)Road traffic flow prediction based on dynamic spatiotemporal graph attention networkScientific Reports10.1038/s41598-023-41932-613:1Online publication date: 7-Sep-2023
https://doi.org/10.1038/s41598-023-41932-6
Bharti SSaini VKumar RVijayvargiya A(2022)Attention Mechanism in Deep Learning for Wind Power Forecasting2022 IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES)10.1109/PEDES56012.2022.10080136(1-6)Online publication date: 14-Dec-2022
https://doi.org/10.1109/PEDES56012.2022.10080136
Wang QYuan YZhang QYang X(2022)Signalized arterial origin-destination flow estimation using flawed vehicle trajectories: A self-supervised learning approach without ground truthTransportation Research Part C: Emerging Technologies10.1016/j.trc.2022.103917145(103917)Online publication date: Dec-2022
https://doi.org/10.1016/j.trc.2022.103917
Li LShao HChen JWang Y(2022)Self-attention Based Multimodule Fusion Graph Convolution Network for Traffic Flow PredictionData Science10.1007/978-981-19-5194-7_1(3-16)Online publication date: 10-Aug-2022
https://doi.org/10.1007/978-981-19-5194-7_1

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Traffic flow matrix-based graph neural network with attention mechanism for traffic flow prediction

Multi-scale Spatio-temporal Attention Network for Traffic Flow Prediction

A grey convolutional neural network model for traffic flow prediction under traffic accidents

Comments

Published In

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Other Metrics

Article Metrics

Other Metrics

Cited By

Login options

Full Access

PDF

eReader

Abstract

References

Cited By

Index Terms

Recommendations

Traffic flow matrix-based graph neural network with attention mechanism for traffic flow prediction

Multi-scale Spatio-temporal Attention Network for Traffic Flow Prediction

A grey convolutional neural network model for traffic flow prediction under traffic accidents

Comments

Information

Published In

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations