广东工业大学学报 ›› 2023, Vol. 40 ›› Issue (04): 1-8.doi: 10.12052/gdutxb.220157

• 计算机科学与技术 •    下一篇

面向多粒度交通流预测的时空深度回归模型

温雯1, 刘莹1, 蔡瑞初1, 郝志峰1,2   

  1. 1. 广东工业大学 计算机学院, 广东 广州 510006;
    2. 汕头大学 工学院, 广东 汕头 515000
  • 收稿日期:2022-10-18 出版日期:2023-07-25 发布日期:2023-08-02
  • 通信作者: 刘莹(1998–)， 女，硕士研究生，主要研究方向为数据挖掘，E-mail：952463330@qq.com
  • 作者简介:温雯(1981–)， 女，教授，博士，主要研究方向为机器学习、数据挖掘
  • 基金资助:
    国家自然科学基金资助项目(61976052)；广东省自然科学基金资助项目(2021A1515011965)

Spatial-temporal Deep Regression Model for Multi-granularity Traffic Flow Prediction

Wen Wen1, Liu Ying1, Cai Rui-chu1, Hao Zhi-feng1,2   

  1. 1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China;
    2. Engineering School, Shantou University, Shantou 515000, China
  • Received:2022-10-18 Online:2023-07-25 Published:2023-08-02

HTML

PDF (PC)

935

摘要： 交通流预测是智能交通系统中的一类重要问题。尽管当前交通流预测方法取得了较好的进展，但还面临2个关键挑战：(1) 交通流的变化模式不仅依赖于时间维度上的历史信息，还依赖于空间维度上相邻区域的信息，如何兼顾两个维度上的变化模式；(2) 时间本身具有小时、天及周等多粒度特性，如何实现多粒度下时序模式的捕捉。本文针对交通流预测的上述挑战，设计了一个多粒度时空深度回归模型(Spatial-temporal Deep Regression Model for Multi-granularity, MGSTDR)，其基本思想是在多粒度时空交通流信息的基础上，对典型的差分整合移动平均自回归模型(Autoregressive Integrated Moving Average model, ARIMA)进行深度拓展，该模型在有效利用自身历史信息的同时，能兼顾相邻区域的信息，从而能够实现多粒度的时序交通流量预测。多个数据集上的实验结果表明，该模型在多粒度预测任务上优于现有的多个基准模型，尤其在小时这一粒度的预测结果上有5.66%的提升。

关键词: 多粒度, 时空相关性, 交通流, 深度学习, 自回归

Abstract: Traffic flow prediction is an important problem in the field of intelligent transportation systems. Most existing traffic-flow prediction methods have made good progress, which however still face the following two key challenges. (1) The underlying pattern of traffic flow depends on not only the historical information along the timeline, but also the information of spatially adjacent areas, making it a challenging problem on how to balance the two temporal-spatial patterns; (2) Due to fact that time information has the characteristic of multiple granularity, such as hour, day and week, how to capture the multi-grained temporal patterns is another challenge problem. In this paper, we design a multi-grained spatio-temporal deep regression model (MGSTDR) to address the above challenges. By extending the typical autoregressive integrated moving average model (ARIMA) on the basis of multi-grained spatio-temporal traffic flow information, the proposed model can effectively use historical information along the timeline as well as the information of adjacent regions, such that the prediction of multi-grained spatio-temporal traffic flow can be performed. Experimental results on several datasets demonstrate that the proposed model outperforms existing benchmark methods on the task of multi-granularity, and particularly obtains an approximately 5.66% improvement in the hourly traffic flow prediction.

Key words: multi-granularity, spatio-temporal correlation, taffic flow, deep learning, autoregressive

中图分类号: 

  • TP389.1
[1] VLAHOGIANNI E I, KARLAFTIS M G, GOLIAS J C. Short-term traffic forecasting: where we are and where we’re going[J]. Transportation Research Part C:Emerging Technologies, 2014, 43: 3-19.
[2] ZHOU Z, WANG Y, XIE X, et al. Foresee urban sparse traffic accidents: a spatiotemporal multi-granularity perspective[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(8): 3786-3799.
[3] GUO S, LIN Y, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. California: AAAI Press, 2019: 922-929.
[4] WILLIAMS B M, HOEL L A. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results[J]. Journal of Transportation Engineering, 2003, 129(6): 664-672.
[5] ZHANG G P. Time series forecasting using a hybrid ARIMA and neural network model[J]. Neurocomputing, 2003, 50: 159-175.
[6] YANG B, SUN S, LI J, et al. Traffic flow prediction using LSTM with feature enhancement[J]. Neurocomputing, 2019, 332: 320-327.
[7] ZHANG S, ZHENG H, SU H, et al. GACAN: graph attention-convolution-attention networks for traffic forecasting based on multi-granularity time series[EB/OL]. arXiv preprint arXiv: 2110.14331(2021-10-27)[2022-3-25].https://doi.org/10.48550/arXiv.2110.14331.
[8] WU Y, TAN H. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework[EB/OL]. arXiv preprint arXiv: 1612.01022(2016-12-03)[2022-3-25].https://doi.org/10.48550/arXiv.1612.01022
[9] MA X, DAI Z, HE Z, et al. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): 818.
[10] ZHANG J, ZHENG Y, QI D, et al. DNN-based prediction model for spatio-temporal data[C]//Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York: Association for Computing Machinery, 2016, 92: 1-4.
[11] ZHANG J, ZHENG Y, QI D. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//Thirty-first AAAI Conference on Artificial Intelligence. California: AAAI Press, 2017, 31(1): 1655-1661.
[12] CHENG X, ZHANG R, ZHOU J, et al. Deeptransport: Learning spatial-temporal dependency for traffic condition forecasting[C]//2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro: IEEE, 2018: 1-8.
[13] ALI A, ZHU Y, ZAKARYA M. Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction[J]. Neural Networks, 2022, 145: 233-247.
[14] DU S D, LI T R, YANG Y, et al. A sequence-to-sequence spatial-temporal attention learning model for urban traffic flow prediction[J]. Journal of Computer Research and Development, 2020, 57(8): 1715-1728.
[15] MA C, KANG P, LIU X. Hierarchical gating networks for sequential recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: Association for Computing Machinery, 2019: 825-833.
[16] GOYAL A, LAMB A, HOFFMANN J, et al. Recurrent independent mechanisms[EB/OL]. arXiv preprint arXiv: 1909.10893(2020-11-17)[2022-3-25].https://doi.org/10.48550/arXiv.1909.10893.
[17] MA C, DAI G, ZHOU J. Short-term traffic flow prediction for urban road sections based on time series analysis and LSTM_BILSTM method[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(6): 5615-5624.
[18] WANG K, SHENG L, GU S, et al. Sequential point cloud upsampling by exploiting multi-scale temporal dependency[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(12): 4686-4696.
[1] 钟耿君, 李东. 基于通道分离机制的双分支点云处理网络[J]. 广东工业大学学报, 2023, 40(04): 18-23.
[2] 金宇凯, 李志生, 欧耀春, 张华刚, 曾江毅, 陈搏超. 基于多阶段聚类的PM2.5质量浓度预测及对比研究[J]. 广东工业大学学报, 2023, 40(03): 17-24.
[3] 吴俊贤, 何元烈. 基于通道注意力的自监督深度估计方法[J]. 广东工业大学学报, 2023, 40(02): 22-29.
[4] 刘冬宁, 王子奇, 曾艳姣, 文福燕, 王洋. 基于复合编码特征LSTM的基因甲基化位点预测方法[J]. 广东工业大学学报, 2023, 40(01): 1-9.
[5] 徐伟锋, 蔡述庭, 熊晓明. 基于深度特征的单目视觉惯导里程计[J]. 广东工业大学学报, 2023, 40(01): 56-60,76.
[6] 刘洪伟, 林伟振, 温展明, 陈燕君, 易闽琦. 基于MABM的消费者情感倾向识别模型——以电影评论为例[J]. 广东工业大学学报, 2022, 39(06): 1-9.
[7] 章云, 王晓东. 基于受限样本的深度学习综述与思考[J]. 广东工业大学学报, 2022, 39(05): 1-8.
[8] 郑佳碧, 杨振国, 刘文印. 基于细粒度混杂平衡的营销效果评估方法[J]. 广东工业大学学报, 2022, 39(02): 55-61.
[9] Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[10] 赖峻, 刘震宇, 刘圣海. 基于全局数据混洗的小样本数据预测方法[J]. 广东工业大学学报, 2021, 38(03): 17-21.
[11] 李振福, 段伟, 李肇坤, 邓昭. 基于“21世纪海上丝绸之路”AIS数据的船舶交通流预测[J]. 广东工业大学学报, 2020, 37(06): 1-8.
[12] 岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(04): 35-41.
[13] 张舒, 莫赞, 柳建华, 杨培琛, 刘洪伟. 基于NWD集成算法的多粒度微博用户兴趣画像构建[J]. 广东工业大学学报, 2020, 37(04): 42-50.
[14] 曾碧, 任万灵, 陈云华. 基于CycleGAN的非配对人脸图片光照归一化方法[J]. 广东工业大学学报, 2018, 35(05): 11-19.
[15] 陈旭, 张军, 陈文伟, 李硕豪. 卷积网络深度学习算法与实例[J]. 广东工业大学学报, 2017, 34(06): 20-26.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发