Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions

被引:207
|
作者
Yin, Xueyan [1 ]
Wu, Genze [1 ]
Wei, Jinze [1 ]
Shen, Yanming [1 ,2 ]
Qi, Heng [1 ]
Yin, Baocai [1 ,3 ]
机构
[1] Dalian Univ Technol, Sch Elect Informat & Elect Engn, Dalian 116024, Peoples R China
[2] Dalian Univ Technol, Minist Educ, Key Lab Intelligent Control & Optimizat Ind Equip, Dalian 116024, Peoples R China
[3] Peng Cheng Lab, Shenzhen 518055, Peoples R China
基金
中国国家自然科学基金;
关键词
Deep learning; Correlation; Predictive models; Data models; Convolution; Roads; Learning systems; Traffic prediction; deep learning; spatial-temporal dependency modeling; CONVOLUTIONAL NEURAL-NETWORKS; FLOW PREDICTION; PASSENGER FLOW; DEMAND; FRAMEWORK; REPRESENTATIONS; REGRESSION;
D O I
10.1109/TITS.2021.3054840
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion. This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network. Recently, a significant amount of research efforts have been devoted to this area, especially deep learning method, greatly advancing traffic prediction abilities. The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives. Specifically, we first summarize the existing traffic prediction methods, and give a taxonomy. Second, we list the state-of-the-art approaches in different traffic prediction applications. Third, we comprehensively collect and organize widely used public datasets in the existing literature to facilitate other researchers. Furthermore, we give an evaluation and analysis by conducting extensive experiments to compare the performance of different methods on a real-world public dataset. Finally, we discuss open challenges in this field.
引用
收藏
页码:4927 / 4943
页数:17
相关论文
共 50 条
  • [31] Deep learning for steganalysis of diverse data types: A review of methods , taxonomy, challenges and future directions
    Kheddar, Hamza
    Hemis, Mustapha
    Himeur, Yassine
    Megias, David
    Amira, Abbes
    NEUROCOMPUTING, 2024, 581
  • [32] Modeling traffic conflicts for use in road safety analysis: A review of analytic methods and future directions
    Zheng, Lai
    Sayed, Tarek
    Mannering, Fred
    ANALYTIC METHODS IN ACCIDENT RESEARCH, 2021, 29
  • [33] Spatiotemporal traffic matrix prediction: A deep learning approach with wavelet multiscale analysis
    Zhao, Jianlong
    Qu, Hua
    Zhao, Jihong
    Jiang, Dingchao
    TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES, 2019, 30 (12):
  • [34] Text classification using deep learning techniques: a bibliometric analysis and future research directions
    Sarin, Gaurav
    Kumar, Pradeep
    Mukund, M.
    BENCHMARKING-AN INTERNATIONAL JOURNAL, 2024, 31 (08) : 2743 - 2766
  • [35] Traffic Matrix Prediction Based on Deep Learning for Dynamic Traffic Engineering
    Liu, Zhifeng
    Wang, Zhiliang
    Yin, Xia
    Shi, Xingang
    Guo, Yingya
    Tian, Ying
    2019 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS (ISCC), 2019, : 219 - 225
  • [36] Bibliometric Analysis of Traffic Accident Prediction Studies from 2003 to 2023: ATrends, Patterns and Future Directions
    Ulu, Mesut
    Turkan, Yusuf Sait
    PROMET-TRAFFIC & TRANSPORTATION, 2024, 36 (05): : 833 - 851
  • [37] Deep reinforcement learning-based methods for resource scheduling in cloud computing: a review and future directions
    Zhou, Guangyao
    Tian, Wenhong
    Buyya, Rajkumar
    Xue, Ruini
    Song, Liang
    ARTIFICIAL INTELLIGENCE REVIEW, 2024, 57 (05)
  • [38] A Survey of Deep Learning for Retinal Blood Vessel Segmentation Methods: Taxonomy, Trends, Challenges and Future Directions
    Sule, Olubunmi Omobola
    IEEE ACCESS, 2022, 10 : 38202 - 38236
  • [39] Motion planning methods for autonomous vehicles in disordered traffic systems: A comparative analysis and future research directions
    Munigety, Caleb Ronald
    International Journal of Vehicle Autonomous Systems, 2020, 15 (02) : 152 - 173
  • [40] Deep Learning Framework with Time Series Analysis Methods for Runoff Prediction
    Li, Zhenghe
    Ling, Kang
    Zhou, Liwei
    Zhu, Modi
    WATER, 2021, 13 (04)