2025年04月05日 星期六

广西师范大学学报（自然科学版） ›› 2025, Vol. 43 ›› Issue (2): 20-29.doi: 10.16088/j.issn.1001-6600.2024041102

• 物理与电子工程 • 上一篇    下一篇

基于时空矩阵分解的路网交通数据修复方法

许伦辉1,2*, 许润南1   

  1. 1.广东科技学院 计算机学院, 广东 东莞 523083;
    2.华南理工大学 土木与交通学院, 广东 广州 510641
  • 收稿日期:2024-04-11 修回日期:2024-06-06 出版日期:2025-03-05 发布日期:2025-04-02
  • 通讯作者: 许伦辉(1965—), 男, 江西南康人, 华南理工大学教授, 博导。E-mail: lhxu@scut.edu.cn
  • 基金资助:
    国家自然科学基金(52072130); 广东省普通高校重点领域专项(2021ZDZX1077); 广东科技学院科研项目(GKY-2023KYYBY-21)

Traffic Data Imputation Method of Road Network Based on Spatial-Temporal Matrix Factorization

XU Lunhui1,2*, XU Runnan1   

  1. 1. School of Computer Science, Guangdong University of Science and Technology, Dongguan Guangdong 523083, China;
    2. School of Civil Engineering and Transportation, South China University of Technology, Guangzhou Guangdong 510641, China
  • Received:2024-04-11 Revised:2024-06-06 Online:2025-03-05 Published:2025-04-02

PDF (PC)

0

摘要： 针对城市路网交通数据缺失问题,综合考虑交通数据客观存在的时空特性,本文提出一种基于时空矩阵分解(spatial-temporal matrix factorization, STMF)的路网交通数据修复方法。首先依据路网时空属性,将多维交通数据处理为二维矩阵形式,将其分解为空间特征矩阵和时间特征矩阵,并通过低秩近似的方式重构不完整交通数据矩阵,实现缺失数据的基本修复。然后,利用图拉普拉斯(graph Laplacian, GL)和门控循环网络(gated recurrent network, GRN)分别作为空间和时间正则器,进一步挖掘路网交通数据的空间结构关联特性和时间依赖特性,有效提高路网交通数据的修复精度。最后,采用洛杉矶交通速度数据集(Metr-LA)和广州交通数据集(Guangzhou-D)对STMF模型的性能与GAIN、BGCP、BTMF、LRTC-TNN和HaLRTC等基准模型进行对比,实验结果表明,本文提出的基于时空矩阵分解STMF模型相比基准模型,能更好地适应不同的缺失场景和不同的缺失率,缺失数据修复性能具有更好的鲁棒性。

关键词: 智能交通, 数据修复, 矩阵分解, 交通数据, 图拉普拉斯, 门控循环网络

Abstract: To tackle the issue of missing traffic data in urban road network, this paper proposes a road network traffic data imputation method based on the spatial-temporal matrix factorization (namely STMF). Based on the spatiotemporal properties of the road network, this study first processes the multidimensional traffic data into a 2D matrix, then decomposes it into a spatial feature matrix and a temporal feature matrix and reconstructs the incomplete traffic data matrix by a low-rank approximation to achieve the basic repair of the missing data. Then graph Laplacian (GL) and gated recurrent network (GRN) are used as spatial and temporal regularizers respectively, to further mine spatial topology information and temporal dependencies of the urban road network and enhance the accuracy of matrix reconstruction and missing value imputation. Finally, the Los Angeles Traffic Speed dataset (Metr-LA) and Guangzhou Traffic dataset (Guangzhou-D) are used to compare the performance of STMF model with benchmark models such as GAIN, BGCP, BTMF, LRTC-TNN and HaLRTC. The experimental results show that, compared with the benchmark model, the proposed STMF model based on temporal matrix decomposition can better adapt to different missing scenarios and different missing rates, and the performance of missing data repair is more robust.

Key words: intelligent transportation, data imputation, matrix factorization, traffic data, graph Laplacian, gated recurrent network

中图分类号:  U491

[1] LI R N, QIN Y, WANG J B, et al. AMGB: trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV[J]. Pattern Recognition Letters, 2023, 169: 17-27. DOI: 10.1016/j.patrec.2023.03.006.
[2] CHEN X Y, SUN L J. Bayesian temporal factorization for multidimensional time series prediction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(9): 4659-4673. DOI: 10.1109/TPAMI.2021.3066551.
[3] LI J L, LI R N, HUANG Z L, et al. Dynamic adaptive generative adversarial networks with multi-view temporal factorizations for hybrid recovery of missing traffic data[J]. Neural Computing and Applications, 2023, 35(10): 7677-7696. DOI: 10.1007/s00521-022-08064-w.
[4] 徐东伟,彭航,商学天,等.基于图自编码-生成对抗网络的路网数据修复[J].交通运输系统工程与信息,2021,21(6):33-41.DOI: 10.16097/j.cnki.1009-6744.2021.06.005.
[5] CHEN X Y, HE Z C, SUN L J. A Bayesian tensor decomposition approach for spatiotemporal traffic data imputation[J]. Transportation Research Part C: Emerging Technologies, 2019, 98: 73-84. DOI: 10.1016/j.trc.2018.11.003.
[6] YOON J, JORDON J, SCHAAR M. GAIN: missing data imputation using generative adversarial nets[J]. Proceedings of Machine Learning Research, 2018, 80: 5689-5698.
[7] 张伟健,邴其春,沈富鑫,等.城市快速路路段行程时间估计方法[J].广西师范大学学报(自然科学版),2023,41(2):49-57.DOI: 10.16088/j.issn.1001-6600.2022032504.
[8] LI R N, QIN Y, WANG C H, et al. A blockchain-enabled framework for enhancing scalability and security in IIoT[J]. IEEE Transactions on Industrial Informatics, 2023, 19(6): 7389-7400. DOI: 10.1109/TII.2022.3210216.
[9] WU P, HUANG Z L, PIAN Y Z, et al. A combined deep learning method with attention-based LSTM model for short-term traffic speed forecasting[J]. Journal of Advanced Transportation, 2020, 2020: 8863724. DOI: 10.1155/2020/8863724.
[10] 陈昆,曲大义,王少杰,等.基于二次分解和融合多特征的短时交通流量组合预测模型[J].广西师范大学学报(自然科学版),2023,41(4):33-46.DOI: 10.16088/j.issn.1001-6600.2022062803.
[11] LI J L, XU L H, LI R N, et al. Deep spatial-temporal bi-directional residualoptimisation based on tensor decomposition for traffic data imputation on urban road network[J]. Applied Intelligence, 2022, 52(10): 11363-11381. DOI: 10.1007/s10489-021-03060-4.
[12] 蔡丽坤,吴运兵,陈甘霖,等.基于生成对抗网络的类别文本生成[J].广西师范大学学报(自然科学版),2022,40(4):79-90.DOI: 10.16088/j.issn.1001-6600.2021093002.
[13] 许伦辉,李金龙,李若南,等.基于动态生成对抗网络的路网缺失交通数据修复[J].广西师范大学学报(自然科学版),2024,42(2):30-40.DOI: 10.16088/j.issn.1001-6600.2023051402.
[14] JIA X Y, DONG X Y, CHEN M, et al. Missing data imputation for traffic congestion data based on joint matrix factorization[J]. Knowledge-Based Systems, 2021, 225: 107114. DOI: 10.1016/j.knosys.2021.107114.
[15] LEI M Y, LABBE A, WU Y K, et al. Bayesian kernelized matrix factorization for spatiotemporal traffic data imputation and kriging[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 18962-18974. DOI: 10.1109/TITS.2022.3161792.
[16] CHEN X Y, YANG J M, SUN L J. A nonconvex low-rank tensor completion model for spatiotemporal traffic data imputation[J]. Transportation Research Part C: Emerging Technologies, 2020, 117: 102673. DOI: 10.1016/j.trc.2020.102673.
[17] GAO Y, YANG L T, YANG J, et al. Jointly low-rank tensor completion for estimating missing spatiotemporal values in logistics systems[J]. IEEE Transactions on Industrial Informatics, 2023, 19(2): 1814-1822. DOI: 10.1109/TII.2022.3190549.
[18] LIU J, MUSIALSKI P, WONKA P, et al. Tensor completion for estimating missing values in visual data[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 208-220. DOI: 10.1109/TPAMI.2012.39.
[19] 王力,李敏,闫佳庆,等.基于生成式对抗网络的路网交通流数据补全方法[J].交通运输系统工程与信息,2018,18(6):63-71.DOI: 10.16097/j.cnki.1009-6744.2018.06.010.
[20] LI J L, SUN L J, LI R N, et al. Application of siSVR-Vis/NIR to the nondestructive determination of acid detergent fiber content in corn straw[J]. Optik, 2020, 202: 163717. DOI: 10.1016/j.ijleo.2019.163717.
[1] 陈秀锋, 王成鑫, 赵凤阳, 杨凯, 谷可鑫. 改进DQN算法的单点交叉口信号控制方法[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 81-88.
[2] 李向利, 梅建平, 莫元健. 基于超图正则NMF的自适应半监督多视图聚类[J]. 广西师范大学学报（自然科学版）, 2024, 42(4): 137-152.
[3] 许伦辉, 李金龙, 李若南, 陈俊宇. 基于动态生成对抗网络的路网缺失交通数据修复[J]. 广西师范大学学报（自然科学版）, 2024, 42(2): 30-40.
[4] 谭凯, 李永杰, 潘海明, 黄可馨, 邱杰, 陈庆锋. 基于多信息集成的药物靶标预测方法研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 91-102.
[5] 彭新建,翁小雄. 基于萤火虫算法优化BP神经网络的公交行程时间预测[J]. 广西师范大学学报（自然科学版）, 2017, 35(1): 28-36.
[6] 邝先验, 朱磊, 吴赟, 徐晨. 基于Adaboost算法和颜色特征的公交车辆视频检测[J]. 广西师范大学学报（自然科学版）, 2016, 34(1): 9-18.
[7] 许伦辉, 游黄阳. 基于特性和影响因素分析的短时交通流预测[J]. 广西师范大学学报（自然科学版）, 2013, 31(1): 1-5.
Viewed
Full text
0
HTML PDF
Just accepted Online first Issue Just accepted Online first Issue
0 0 0 0 0 0


Abstract
5
Just accepted Online first Issue
0 0 5
  From Others local
  Times 4 1
  Rate 80% 20%

Cited
Web of Science  Crossref   ScienceDirect  Search for Citations in Google Scholar >>
 
This page requires you have already subscribed to WoS.
  Shared   
  Discussed   
[1] 贺青, 李栋, 罗思源, 贺寓东, 李彪, 王强. 超宽带里德堡原子天线技术研究进展[J]. 广西师范大学学报（自然科学版）, 2025, 43(2): 1 -19 .
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发