Review of data-driven short-term prediction methods for continuous traffic flow in road networks
Article Text (Baidu Translation)
-
摘要: 为掌握数据驱动下的路网连续交通流短时预测技术发展最新动态，基于人工智能计算和实时交通数据采集技术快速发展的背景，对短时交通流深度学习预测模型、数据处理技术和预测效果进行了综述与总结。该研究梳理了交通流预测的经典统计模型、机器学习模型及深度学习模型的演变历程，重点分析了各类模型的优势与局限性；归纳了2024年至今的短时交通流预测方法研究进展，详细对比研究了循环神经网络、图卷积网络、多头注意力机制与Transformer架构、神经微分方程、超图理论及轻量化架构等短时交通流预测模型，以及联邦学习、迁移学习、生成对抗网络和多源数据融合等短时交通流预测数据处理技术；基于对均方根误差、平均绝对误差和平均绝对百分比误差三大核心指标的对比，总结了主流模型在标准化数据集PEMS上的性能，评估了代表性模型的泛化能力与稳定性。结果表明：深度学习方法相对于传统模型在短时交通流预测的精度、泛化能力及稳定性上具有明显优势；具备动态时空关系建模、多尺度周期数据结构、计算效率改进方法及增强鲁棒性机制等特征的短时交通流预测模型有更优异的性能；数据处理技术可有效改善数据隐私、跨区域差异、数据稀缺与异常缺失等实际问题，提升短时交通流预测模型的工程应用性能与可扩展性。未来可从时空特征挖掘、数据融合、模型轻量化、知识迁移以及模型工程应用等方面深化研究。Abstract: In the context of the rapid development of artificial intelligence computing and real-time traffic data acquisition technology, the deep learning prediction models, data processing technology, and prediction performance for short-term traffic flow were reviewed and summarized to grasp the latest developments of data-driven short-term traffic flow prediction technology for road networks. The evolution of classical statistical models, machine learning models, and deep learning models for traffic flow prediction was reviewed, and the advantages and limitations of various models were emphatically analyzed. The research progress of short-term traffic flow prediction methods from 2024 to the present was summarized. Short-term traffic flow prediction models such as recurrent neural networks, graph convolutional networks, multi-head attention mechanisms and Transformer architectures, neural ordinary differential equations, hypergraph theory, and lightweight architectures were compared and investigated in detail, as well as data processing technologies for short-term traffic flow prediction including federated learning, transfer learning, generative adversarial networks, and multi-source data fusion. Based on the comparison of three core indicators including root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), the performance of mainstream models on the standardized dataset PEMS was summarized, and the generalization capability and stability of representative models were evaluated. The research results show that deep learning methods have significant advantages over traditional models in terms of accuracy, generalization capability, and stability for short-term traffic flow prediction. Short-term traffic flow prediction models with characteristics such as dynamic spatio-temporal relationship modeling, multi-scale periodic data structures, computational efficiency improvement methods, and enhanced robustness mechanisms demonstrate superior performance. Data processing technologies can effectively mitigate practical problems such as data privacy, cross-regional differences, data scarcity, and abnormal missing values, enhancing the engineering application performance and scalability of short-term traffic flow prediction models. Future research can be deepened in aspects such as spatio-temporal feature mining, data fusion, model light weighting, knowledge transfer, and model engineering applications.
-
图 3 各模型在各数据集上的评价指标平均排名
Figure 3. Mean ranking of model evaluation metrics across datasets
表 1 短时交通流预测模型对比
Table 1. Comparison of short-term traffic flow prediction models
方法类别 代表模型 空间建模 时间建模 优点 缺点 RNN组合模型 IDBiLSTM[46] BiLSTM、滞后极限学习机 预测精度高、数据利用率高、实时性好、鲁棒性强 缺乏空间建模、数据依赖性强、计算资源需求高、泛化能力有限 GAE-GRU[47] 图注意力自编码器 GRU 改进GAE能深度提取空间特征、GRU参数少训练速度快、具备较强的鲁棒性和泛化能力 空间模型需大量数据预训练、图卷积层数增加会导致过平滑、难以处理动态路网结构 GCN组合模型 MSTAGNN[19] 时空嵌入、动态局部时空图、局部卷积、全局时空信息融合 多步卷积循环模块、多步图卷积循环单元 全局时空趋势和局部动态捕捉、动态图建模、计算成本低、预测精度高 模型结构复杂需调参、特定场景适配性待验证 DSTGRNN[52] 动态图生成器、多头注意力、动态节点嵌入、静态图卷积、多图融合门控 DGRNN、图卷积LSTM 动态空间依赖捕捉、静态图和动态图特征高效融合、突发场景鲁棒性强、计算效率高 模型复杂训练难度高、依赖节点嵌入和超参数调节、实际部署存在延迟 HSTGNN[25] 自适应图学习、动态图学习、混合图学习 离散小波变换解耦、时间注意力、时间卷积、时间门控 异质时间模式建模、空间表示能力强、长短期预测优异、抗噪声和缺失数据 模型复杂度高、参数调优耗时、未考虑外部因素 注意力组合模型 TC-GCN[62] GCN、扩散卷积、自适应空间矩阵 交叉注意力 能捕捉三维交互关系、拓扑建模强、特征提取优异 模型结构复杂、超参数敏感、长序列预测效果不明 STGAFormer[64] 距离空间自注意力、自适应邻接矩阵、拉普拉斯矩阵 门控卷积、多头时间注意力、周期性特征嵌入 异常事件适应性强、能处理空间异质性、多维度特征融合 训练成本高、参数调优复杂、不适合极大规模图 ODE组合模型 HSTGODE[17] 动态自适应图、空间ODE、区域和节点层次化建模 时空ODE连续建模、多尺度时间卷积、门控 连续时空建模、消除过平滑、动态图结构优化、区域和节点协同建模 结构复杂、依赖聚类、ODE求解训练较慢 CAG-NSPDE[71] 双分量可学习节点嵌入、连续自适应图卷积 双层神经SPDE、时间域和频率域联合建模 捕捉连续空间变化、鲁棒性强、多域特征提取、参数效率高 训练速度较慢、模型复杂度较高、超参数敏感 超图组合模型 SHCN[22] 静态超边构建、动态超边构建、谱域超图卷积 门控时间卷积 能捕获高阶空间关系、多尺度特征提取、鲁棒性强 计算复杂度高、超边质量依赖数据、模型结构复杂 A2HGCN[72] 超边构造、超图卷积、线图卷积 双注意力机制、卷积LSTM 捕获非邻近节点相关性、预测精度高、可解释性强 静态超图限制、长时预测能力有限、超图构造依赖阈值 轻量化组合模型 MFGCN[33] 时间特定的空间图、空间图卷积 节点特定的时间图、时间图卷积 多面时空关系建模、自适应模式共享、符合真实交通规律 数据质量敏感、计算复杂度较高、受噪声干扰易不稳定 ST-GMLP[59] 自适应图卷积网络、空间GMLP 多尺度时间模式、GMLP 结构简单高效、资源占用少、适应性强 空间建模较弱、依赖周期性特征数据 
下载: 导出CSV
表 2 模型训练参数对比
Table 2. Comparison of model training parameters
模型 批量大小 训练轮数 优化函数 学习率 训练环境 ST-GMLP[59] 128 Adam 0.001 NVIDIA 3060Ti DFAGCN[66] 32 50 Adam 0.002、0.01 NVIDIA GeForce GTX 3090 STGAFormer[64] 16
PEMS07(4)200 AdamW 0.001 NVIDIA RTX A6000 STAMT[35] 64 Ranger21 0.001 NVIDIA TeslaV100 MSTAGNN[19] 64
PEMS07(16)20 0.06
PEMS04(0.07)NVIDIA V100 MFGCN[33] 200 Adam 0.000 1、0.000 5、0.001 Tesla T4 STSFGACN[31] 64 200 0.003 H2STGCN[56] 32 100 Adam 0.002 NVIDIA GeForce RTX 3090 CAG-NSPDE[71] 200 0.000 1、0.005、0.001、0.05、0.01 NVIDIA RTX 4090 DSTGNDE[18] 32 200 Adam 0.001 NVIDIA GeForce RTX 3090
下载: 导出CSV
表 3 模型效果对比
Table 3. Model performance comparison
模型 PEMS03 PEMS04 PEMS07 PEMS08 MAE RMSE MAPE/% MAE RMSE MAPE/% MAE RMSE MAPE/% MAE RMSE MAPE/% ST-GMLP[59] 14.66 23.93 14.09 18.41 30.03 12.08 18.87 31.86 7.78 13.11 22.44 8.56 DFAGCN[66] 15.19 24.16 14.99 19.55 30.86 13.64 22.14 35.30 9.55 16.06 25.09 10.57 STGAFormer[64] 14.56 24.94 14.69 18.18 29.78 11.98 19.65 32.62 8.40 13.06 22.43 8.87 STAMT[35] 14.58 23.81 15.30 17.98 29.45 12.09 19.07 32.15 8.09 13.34 22.59 8.82 MSTAGNN[19] 14.53 24.17 14.84 18.22 30.47 12.07 19.47 33.31 8.22 13.50 23.39 8.99 MFGCN[33] 14.50 23.42 14.36 18.29 29.67 12.10 19.85 33.19 8.26 14.24 23.32 9.01 STSFGACN[31] 14.98 26.24 14.07 19.14 31.64 12.56 20.61 33.84 8.73 15.14 24.61 9.66 H2STGCN[56] 14.59 25.26 14.42 18.64 30.67 12.11 19.87 32.97 8.29 14.32 23.78 9.23 CAG-NSPDE[71] 15.02 26.57 14.33 18.96 30.83 12.37 20.16 33.58 8.31 15.08 24.42 9.67 DSTGNDE[18] 14.78 24.74 14.24 18.84 30.24 12.84 20.04 33.23 8.42 15.12 24.03 9.64 注：加粗值为最优值，下划线为次优值。
下载: 导出CSV
-
[1] SUN N. Intelligent transportation system planning in the age of artificial intelligence[C]//LI J, WU J, CHEN K. 2021 International Conference on Environmental and Engineering Management. Changsha: EDP Sciences, 2021: 1036-1041. [2] TEDJOPURNOMO D A, BAO Z, ZHENG B, et al. A survey on modern deep neural network for traffic prediction: Trends, methods and challenges[C]//IEEE. 2023 39th IEEE International Conference on Data Engineering (ICDE). New York: IEEE, 2023: 3795-3796. [3] LINGRAS P, SHARMA S, ZHONG M. Prediction of recreational travel using genetically designed regression and time-delay neural network models[J]. Transportation Research Record, 2002, 1805(1): 16-24. doi: 10.3141/1805-03 [4] MA X L, TO Z M, WANG Y H, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies, 2015, 54: 187-197. doi: 10.1016/j.trc.2015.03.014 [5] SHU W, CAI K, XIONG N N. A short-term traffic flow prediction model based on an improved gate recurrent unit neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2021(9): 1-12. [6] SHI X J, CHEN Z, WANG H, et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting[C]//Curran Associates. Advances in Neural Information Processing Systems 28. New York: Curran Associates, 2015: 802-810. [7] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//ICLR. Proceedings of the 5th International Conference on Learning Representations. Toulon: ICLR, 2017: 1-14. [8] 熊章友, 李卫军, 朱晓娟, 等. 基于深度学习的短时交通流预测研究综述[J]. 计算机工程与应用, 2025, 61(11): 67-82.XIONG Zhang-you, LI Wei-jun, ZHU Xiao-juan, et al. Short-term traffic flow prediction based on deep learning[J]. Computer Engineering and Applications, 2025, 61(11): 67-82. [9] 姚俊峰, 何瑞, 史童童, 等. 基于机器学习的交通流预测方法综述[J]. 交通运输工程学报, 2023, 23(3): 44-67. doi: 10.19818/j.cnki.1671-1637.2023.03.003YAO Jun-feng, HE Rui, SHI Tong-tong, et al. Review on machine learning-based traffic flow prediction methods[J]. Journal of Traffic and Transportation Engineering, 2023, 23(3): 44-67. doi: 10.19818/j.cnki.1671-1637.2023.03.003 [10] AHMED S F, KULDEEP S A, RAFA S J, et al. Enhancement of traffic forecasting through graph neural network-based information fusion techniques[J]. Information Fusion, 2024, 110: 102466. doi: 10.1016/j.inffus.2024.102466 [11] STEPHANEDES Y J, MICHALOPOULOS P G, PLUM R A. Improved estimation of traffic flow for real time control[J]. Transportation Research Record Journal of the Transportation Research Board, 1980(795): 28-39. [12] AHMED M S, COOK A R. Analysis of freeway traffic time-series data by using Box-jenkins techniques[J]. Transportation Research Record, 1979(722): 1-9. [13] OKUTANI I, STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory[J]. Transportation Research Part B Methodological, 1984, 18(1): 1-11. doi: 10.1016/0191-2615(84)90002-X [14] CAI P, WANG Y, LU G, et al. A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting[J]. Transportation Research Part C: Emerging Technologies, 2016, 62: 21-34. doi: 10.1016/j.trc.2015.11.002 [15] HU W, YAN L, LIU K, et al. A short-term traffic flow forecasting method based on the hybrid PSO-SVR[J]. Neural Processing Letters, 2016, 43(1): 155-172. doi: 10.1007/s11063-015-9409-6 [16] DOUGHERTY M S, KIRBY H R, BOYLE R D. The use of neural networks to recognize and predict traffic congestion[J]. Traffic engineering & control, 1993, 34(6): 311-314. [17] XU T, DENG J, MA R, et al. Hierarchical spatio-temporal graph ODE networks for traffic forecasting[J]. Information Fusion, 2025, 113: 102614. doi: 10.1016/j.inffus.2024.102614 [18] SHI H, ZHANG W. Learning continuous spatial-temporal evolution via dynamic graph neural differential equations for traffic flow forecasting[J]. Information Sciences, 2025, 700: 121845. doi: 10.1016/j.ins.2024.121845 [19] ZHAO L, GUO B, DAI C, et al. Multi-step trend aware graph neural network for traffic flow forecasting[J]. Big Data Research, 2024, 38: 100482. doi: 10.1016/j.bdr.2024.100482 [20] KONG W, JU Y, ZHANG S, et al. Graph enhanced spatial-temporal transformer for traffic flow forecasting[J]. Applied Soft Computing, 2025, 170: 112698. doi: 10.1016/j.asoc.2025.112698 [21] 郭海锋, 许宏伟, 周子盛. 深度时空混合图卷积的城市交通预测模型[J]. 小型微型计算机系统, 2025, 46(1): 97-103.GUO Hai-feng, XU Hong-wei, ZHOU Zi-sheng. Urban traffic prediction based on deep spatio-temporal hybrid graph convolution[J]. Mini-Micro Systems, 2025, 46(1): 97-103. [22] 尹宝才, 王竟成, 张勇, 等. 基于谱域超图卷积网络的交通流预测模型[J]. 北京工业大学学报, 2024, 50(2): 152-164.YIN Bao-cai, WANG Jing-cheng, ZHANG Yong, et al. Traffic flow prediction model based on spectral hypergraph convolutional network[J]. Journal of Beijing University of Technology, 2024, 50(2): 152-164. [23] ZHANG J, ZHENG Y, QI D. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]//AAAI Press. Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco: AAAI Press, 2017: 1655-1661. [24] MIHAITA A S, LI H, HE Z, et al. Motorway traffic flow prediction using advanced deep learning[C]//IEEE. 2019 IEEE Intelligent Transportation Systems Conference (ITSC). New York: IEEE, 2019: 1683-1690. [25] WANG P, FENG L, ZHU Y, et al. Hybrid spatial-temporal graph neural network for traffic forecasting[J]. Information Fusion, 2025, 118: 102978. doi: 10.1016/j.inffus.2025.102978 [26] 张红, 巩蕾, 曹洁, 等. 基于蜉蝣优化算法的时空融合交通流预测研究[J]. 哈尔滨工程大学学报, 2025, 46(4): 764-771.ZHANG Hong, GONG Lei, CAO Jie, et al. Research on traffic speed forecasting with spatio-temporal fusion based on mayfly optimization algorithm[J]. Journal of Harbin Engineering University, 2025, 46(4): 764-771. [27] 杨平, 李成鑫, 刘宜成, 等. 面向动态交通流多步预测的时空图模型[J]. 计算机工程与设计, 2024, 45(4): 1195-1201.YANG Ping, LI Cheng-xin, LIU Yi-cheng, et al. Spatio-temporal graph model for multi-step forecasting of dynamic traffic flow[J]. Computer Engineering and Design, 2024, 45(4): 1195-1201. [28] 肖培成, 曹阳, 沈琴琴, 等. 基于ARMA过滤器的时空图卷积网络短时交通流预测[J]. 计算机工程与应用, 2024, 60(21): 308-314.XIAO Pei-cheng, CAO Yang, SHEN Qin-qin, et al. Short-term traffic flow prediction based on spatial-temporal graph convolutional network with ARMA filter[J]. Computer Engineering and Applications, 2024, 60(21): 308-314. [29] LUO Q, HE S, HAN X, et al. LSTTN: A long-short term transformer-based spatiotemporal neural network for traffic flow forecasting[J]. Knowledge-Based Systems, 2024, 293: 111637. doi: 10.1016/j.knosys.2024.111637 [30] LOU J, ZHANG X, WANG R, et al. HSFE: A hierarchical spatial-temporal feature enhanced framework for traffic flow forecasting[J]. Information Sciences, 2024, 679: 121070. doi: 10.1016/j.ins.2024.121070 [31] WANG B, LONG Z, SHENG J, et al. Spatial-temporal similarity fusion graph adversarial convolutional networks for traffic flow forecasting[J]. Journal of the Franklin Institute, 2024, 361(17): 107299. doi: 10.1016/j.jfranklin.2024.107299 [32] 肖琳, 陈洪超, 邹复民. 基于多头注意力时空图神经网络的交通流预测[J]. 重庆交通大学学报(自然科学版), 2024, 43(9): 78-85.XIAO Lin, CHEN Hong-chao, ZOU Fu-min. Traffic flow prediction based on multi-head attention spatiotemporal graph neural network[J]. Journal of Chongqing Jiaotong University (Natural Science), 2024, 43(9): 78-85. [33] TIAN J, HAN L, CHEN M, et al. MFGCN: Multi-faceted spatial and temporal specific graph convolutional network for traffic-flow forecasting[J]. Knowledge-Based Systems, 2024, 306: 112671. doi: 10.1016/j.knosys.2024.112671 [34] 田俊山, 曾俊铖, 丁峰, 等. 基于时空关系的高速公路交通流量预测[J]. 工程科学学报, 2024, 46(9): 1623-1629.TIAN Jun-shan, ZENG Jun-cheng, DING Feng, et al. Highway traffic flow forecasting based on spatiotemporal relationship[J]. Journal of Engineering Science, 2024, 46(9): 1623-1629. [35] LIU A, ZHANG Y. An efficient spatial-temporal transformer with temporal aggregation and spatial memory for traffic forecasting[J]. Expert Systems with Applications, 2024, 250: 123884. doi: 10.1016/j.eswa.2024.123884 [36] 王泉, 陆啟想, 施珮. 用于交通流量预测的多图扩散注意力网络[J]. 计算机应用, 2025, 45(5): 1472-1479.WANG Quan, LU Qi-xiang, SHI Pei. Multi graph diffusion attention network for traffic flow prediction[J]. Journal of Computer Applications, 2025, 45(5): 1472-1479. [37] 邓涵优, 陈红梅, 肖清, 等. 基于多头注意力动态图卷积网络的交通流预测[J]. 太原理工大学学报, 2024, 55(1): 172-183.DENG Han-you, CHEN Hong-mei, XIAO Qing, et al. Dynamic graph convolution network with multi-head attention for traffic flow prediction[J]. Journal of Taiyuan University of Technology, 2024, 55(1): 172-183. [38] XU C, XU C Q. Local spatial and temporal relation discovery model based on attention mechanism for traffic forecasting[J]. Neural Networks, 2024, 176: 106365. doi: 10.1016/j.neunet.2024.106365 [39] 翟志鹏, 曹阳, 沈琴琴, 等. 基于多时空图融合与动态注意力的交通流预测[J]. 计算机工程, 2025, 51(9): 139-148.ZHAI Zhi-peng, CAO Yang, SHEN Qin-qin, et al. Traffic flow prediction model based on multiple spatio-temporal graph fusion and dynamic attention[J]. Computer Engineering, 2025, 51(9): 139-148. [40] MA Y, LOU H, YAN M, et al. Spatio-temporal fusion graph convolutional network for traffic flow forecasting[J]. Information Fusion, 2024, 104: 102196. doi: 10.1016/j.inffus.2023.102196 [41] LI Z, ZHOU J, LIN Z, et al. Dynamic spatial aware graph transformer for spatiotemporal traffic flow forecasting[J]. Knowledge-based systems, 2024, 297: 111946. doi: 10.1016/j.knosys.2024.111946 [42] 李云, 高雅, 姚枝秀, 等. 面向数据稀缺场景的智能交通流量预测[J]. 软件学报, 2025, 36(8): 3787-3801.LI Yun, GAO Ya, YAO Zhi-xiu, et al. Intelligent traffic flow prediction for data scarcity scenarios[J]. Journal of Software, 2025, 36(8): 3787-3801. [43] 马飞, 杨治杰, 王江博, 等. 基于气象-交通多通道数据融合的短时交通流速度预测模型[J]. 交通运输工程学报, 2024, 24(6): 183-196. doi: 10.19818/j.cnki.1671-1637.2024.06.013MA Fei, YANG Zhi-jie, WANG Jiang-bo, et al. Short-term traffic flow velocity prediction method based on multi-channel fusion of meteorological and transportation data[J]. Journal of Traffic and Transportation Engineering, 2024, 24(6): 183-196. doi: 10.19818/j.cnki.1671-1637.2024.06.013 [44] SANG W, ZHANG H, KANG X, et al. Dynamic multi-granularity spatial-temporal graph attention network for traffic forecasting[J]. Information Sciences, 2024, 662: 120230. doi: 10.1016/j.ins.2024.120230 [45] LI G, WANG J, ZHAO Z, et al. Advancing complex urban traffic forecasting: A fully attentional spatial-temporal network enhanced by graph representation[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 134: 104237. doi: 10.1016/j.jag.2024.104237 [46] 张阳, 王梓良, 姚芳钰, 等. 融合滞后极限学习机的IDBiLSTM短时交通流预测[J]. 重庆交通大学学报(自然科学版), 2024, 43(6): 39-46.ZHANG Yang, WANG Zi-liang, YAO Fang-yu, et al. IDBiLSTM short-term traffic flow prediction with fused hysteretic extreme learning machine[J]. Journal of Chongqing Jiaotong University (Natural Science), 2024, 43(6): 39-46. [47] 赵子琪, 杨斌, 张远广. 基于图自编码器和GRU网络的分层交通流预测模型[J]. 计算机科学, 2024, 51(增1): 692-697.ZHAO Zi-qi, YANG Bin, ZHANG Yuan-guang. Hierarchical traffic flow prediction model based on graph autoencoder and GRU network[J]. Computer Science, 2024, 51(S1): 692-697. [48] 张俊溪, 曲仕茹, 张志腾, 等. 时空相关的道路网络短时交通流预测模型[J]. 北京交通大学学报, 2024, 48(3): 74-82.ZHANG Jun-xi, QU Shi-ru, ZHANG Zhi-teng, et al. A spatial-temporal dependent short-term traffic flow prediction model for road networks[J]. Journal of Beijing Jiaotong University, 2024, 48(3): 74-82. [49] 罗向龙, 徐忠承, 苏勇东, 等. 改进膨胀时空图卷积网络的短时交通流预测[J]. 计算机工程, 2025, 51(12): 346-356.LUO Xiang-long, XU Zhong-cheng, SU Yong-dong, et al. Short-term traffic flow prediction based on improved dilated temporal-spatio graph convolutional Network[J]. Computer Engineering, 2025, 51(12): 346-356. [50] ZHANG X, CHEN X, TANG H, et al. AdpSTGCN: Adaptive spatial-temporal graph convolutional network for traffic forecasting[J]. Knowledge-Based Systems, 2024, 301: 11. [51] ZHENG X, SHAO H, YAN S, et al. Multiscale information enhanced spatial-temporal graph convolutional network for multivariate traffic flow forecasting via magnifying perceptual scope[J]. Engineering Applications of Artificial Intelligence, 2024, 136: 109010. doi: 10.1016/j.engappai.2024.109010 [52] XIA Z, ZHANG Y, YANG J, et al. Dynamic spatial-temporal graph convolutional recurrent networks for traffic flow forecasting[J]. Expert Systems with Applications, 2024, 240: 122381. doi: 10.1016/j.eswa.2023.122381 [53] 侯越, 张鑫, 武月. 基于时空动态约束图反馈的交通流预测[J/OL]. 吉林大学学报(工学版), 2024, https://doi.org/10.13229/j.cnki.jdxbgxb.20240640 .HOU Yue, ZHANG Xin, WU Yue. Traffic flow prediction based on spatio-temporal dynamic constraint graph feedback[J/OL]. Journal of Jilin University (Engineering and Technology Edition), 2024,https://doi.org/10.13229/j.cnki.jdxbgxb.20240640 .[54] 符琦, 巴冰, 黄崇景, 等. 面向短时交通流预测的动态时空图卷积网络[J]. 湖南科技大学学报(自然科学版), 2024, 39(1): 70-79.FU Qi, BA Bing, HUANG Chong-jing, et al. Dynamic spatiotemporal graph convolutional networks for short-term traffic flow prediction[J]. Journal of Hunan University of Science & Technology (Natural Science Edition), 2024, 39(1): 70-79. [55] 吴永庆, 姜正宇. 基于解耦合动态时空卷积循环网络的交通流预测[J/OL]. 计算机工程, 2024, https://doi.org/10.19678/j.issn.1000-3428.0070319 .WU Yong-qing, JIANG Zheng-yu. Traffic flow prediction based on decoupled dynamic spatial-temporal convolutional recurrent network[J/OL]. Computer Engineering, 2024,https://doi.org/10.19678/j.issn.1000-3428.0070319 .[56] CHEN Y, HUO J, LIN F, et al. Beyond homophily in spatial-temporal traffic flow forecasting[J]. Neural Networks, 2025, 183: 106950. doi: 10.1016/j.neunet.2024.106950 [57] 侯越, 张鑫, 袭著涛, 等. 特殊路网拓扑解构下的时空异质化交通流预测[J]. 铁道科学与工程学报, 2025, 22(7): 2932-2945.HOU Yue, ZHANG Xin, XI Zhu-tao, et al. Spatio-temporal heterogeneous traffic flow prediction under special road network topology deconstruction[J]. Journal of Railway Science and Engineering, 2025, 22(7): 2932-2945. [58] 唐晨嘉, 曾伟, 赵振兴. 基于自适应动态图卷积循环网络的交通流预测[J]. 武汉理工大学学报(交通科学与工程版), 2024, 48(3): 415-420.TANG Chen-jia, ZENG Wei, ZHAO Zhen-xing. Traffic flow prediction based on adaptive dynamic graph convolutional recurrent network[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2024, 48(3): 415-420. [59] LUO Y, ZHENG J, WANG X, et al. ST-GMLP: A concise spatial-temporal framework based on gated multi-layer perceptron for traffic flow forecasting[J]. Neural Networks, 2025, 184: 107074. doi: 10.1016/j.neunet.2024.107074 [60] 张红, 朱思雨, 张玺君, 等. 自适应图卷积优化元图学习的非平稳交通流预测研究[J/OL]. 计算机工程, 2024, https://doi.org/10.19678/j.issn.1000-3428.0070124 .ZHANG Hong, ZHU Si-yu, ZHANG Xi-jun, et al. Research on non-stationary traffic flow forecasting based on adaptive graph convolution optimization meta-graph learning[J/OL]. Computer Engineering, 2024,https://doi.org/10.19678/j.issn.1000-3428.0070124 .[61] 梁秀霞, 夏曼曼, 何月阳, 等. 基于时空多头图注意力网络的交通流预测[J]. 电子学报, 2024, 52(2): 500-509.LIANG Xiu-xia, XIA Man-man, HE Yue-yang, et al. Traffic flow prediction based on spatio-temporal multi-head graph attention network[J]. Acta Electronica Sinica, 2024, 52(2): 500-509. [62] WANG L, GUO D, WU H, et al. TC-GCN: Triple cross-attention and graph convolutional network for traffic forecasting[J]. Information Fusion, 2024, 105: 102229. doi: 10.1016/j.inffus.2024.102229 [63] 鲁思源, 沈琴琴, 包银鑫, 等. 基于时空感知Transformer的交通流预测模型[J]. 电子测量技术, 2024, 47(10): 85-92.LU Si-yuan, SHEN Qin-qin, BAO Yin-xin, et al. Traffic flow prediction model based on spatial-temporal aware Transformer[J]. Electronic Measurement Technology, 2024, 47(10): 85-92. [64] GENG Z, XU J, WU R, et al. STGAFormer: Spatial-temporal gated attention transformer based graph neural network for traffic flow forecasting[J]. Information Fusion, 2024, 105: 102228. doi: 10.1016/j.inffus.2024.102228 [65] 杨国亮, 习浩, 龚家仁, 等. 基于Transformer的短时交通流时空预测[J]. 计算机应用与软件, 2024, 41(3): 169-173.YANG Guo-liang, XI Hao, GONG Jia-ren, et al. Spatio-temporal traffic flow prediction method based on multi-graph fusion[J]. Computer Applications and Software, 2024, 41(3): 169-173. [66] LIU Y, WU X, TANG Y, et al. Decomposition with feature attention and graph convolution network for traffic forecasting[J]. Knowledge-Based Systems, 2024, 300: 112193. doi: 10.1016/j.knosys.2024.112193 [67] 庄伟卿, 曹勇博. 基于改进的时空图卷积网络的交通流预测模型研究[J]. 系统科学与数学, 2024, 44(1): 217-235.ZHUANG Wei-qing, CAO Yong-bo. Research on traffic flow prediction model based on improved spatial-temporal graph convolutional networks[J]. Journal of Systems Science and Mathematical Sciences, 2024, 44(1): 217-235. [68] 张静, 陈诺, 鲍钱涵, 等. 融合交通事件信息的短时交通流参数预测[J]. 公路, 2024, 69(10): 241-250.ZHANG Jing, CHEN Nuo, BAO Qian-han, et al. Prediction of Short-term traffic flow parameter based on traffic event information[J]. Highway, 2024, 69(10): 241-250. [69] 王九胜, 许辉, 缪中岩. 基于时空关系的多细粒度隧道交通流预测模型研究与应用[J]. 公路交通科技, 2024, 41(11): 86-93.WANG Jiu-sheng, XU Hui, MIAO Zhong-yan. Study and application of multi fine-grained tunnel traffic flow prediction model based on spatio-temporal relation[J]. Journal of Highway and Transportation Research and Development, 2024, 41(11): 86-93. [70] 刘云翔, 梁智超. 一种高效的连续时序图注意力网络的交通预测模型[J]. 计算机工程, 2025, 51(4): 350-359.LIU Yun-xiang, LIANG Zhi-chao. A highly efficient traffic prediction model for continuous time-series graph attention networks[J]. Computer Engineering, 2025, 51(4): 350-359. [71] YAN T, GONG H, ZHAN Y, et al. CAG-NSPDE: Continuous adaptive graph neural stochastic partial differential equations for traffic flow forecasting[J]. Neurocomputing, 2024, 603: 128256. doi: 10.1016/j.neucom.2024.128256 [72] 闫光辉, 李鸿涛, 张斌, 等. 考虑非邻近节点空间相关性的交通流预测模型[J]. 计算机应用研究, 2025, 42(3): 825-833.YAN Guang-hui, LI Hong-tao, ZHANG Bin, et al. Traffic prediction model considering spatial correlation of non-neighboring nodes[J]. Application Research of Computers, 2025, 42(3): 825-833. [73] QI Y, HOSSAIN M S, NIE J, et al. Privacy-preserving blockchain-based federated learning for traffic flow prediction[J]. Future Generation Computer Systems, 2021, 17: 328-337. [74] GUO H, MEESE C, LI W, et al. B2sfl: A bi-level block chained architecture for secure federated learning-based traffic prediction[J]. IEEE Transactions on Services Computing, 2023, 16(6): 4360-4374. doi: 10.1109/TSC.2023.3318990 [75] FENG J, YANG L T, ZHU Q, et al. Privacy-preserving tensor decomposition over encrypted data in a federated cloud environment[J]. IEEE Transactions on Dependable and Secure Computing, 2018, 17(4): 857-868. [76] ZHANG C, DANG S, SHIHADA B, et al. Dual attention-based federated learning for wireless traffic prediction[C]//IEEE. IEEE INFOCOM 2021-IEEE conference on computer communications. New York: IEEE, 2021: 1-10. [77] 智慧, 段苗苗, 杨利霞, 等. 一种基于区块链和联邦学习融合的交通流预测方法[J]. 电子与信息学报, 2024, 46(9): 3777-3787.ZHI Hui, DUAN Miao-miao, YANG Li-xia, et al. A traffic flow prediction method based on the fusion of blockchain and federated learning[J]. Journal of Electronics & Information Technology, 2024, 46(9): 3777-3787. [78] WAN X, LIU H, XU H, et al. Network traffic prediction based on LSTM and transfer learning[J]. IEEE Access, 2022, 10: 86181-86190. doi: 10.1109/ACCESS.2022.3199372 [79] WANG S, MIAO H, LI J, et al. Spatio-temporal knowledge transfer for urban crowd flow prediction via deep attentive adaptation networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(5): 4695-4705. [80] TANG Y, QU A, CHOW A H F, et al. Domain adversarial spatial-temporal network: A transferable framework for short-term traffic forecasting across cities[C]//ACM. Proceedings of the 31st ACM international conference on information & knowledge management. New York: ACM, 2022: 1905-1915. [81] YOON J, JORDON J, SCHAAR M. Gain: Missing data imputation using generative adversarial nets[C]//PMLR. International conference on machine learning. Princeton: PMLR, 2018: 5689-5698. [82] 张红, 杨俊译. 用于异常交通流预测的时空生成对抗聚类图卷积网络[J/OL]. 计算机工程, 2025, https://doi.org/10.19678/j.issn.1000-3428.0070180 .ZHANG Hong, YANG Jun-yi. Spatio-temporal generative adversarial clustering graph convolutional networks for anomalous traffic flow forecasting[J/OL]. Computer Engineering, 2025,https://doi.org/10.19678/j.issn.1000-3428.0070180 .[83] LI L, BI J, YANG K, et al. Di-GraphGAN: An enhanced adversarial learning framework for accurate spatial-temporal traffic forecasting under data missing scenarios[J]. Information Sciences, 2024, 677: 120911. doi: 10.1016/j.ins.2024.120911 [84] ZHANG Z, LIN X, LI M, et al. A customized deep learning approach to integrate network-scale online traffic data imputation and prediction[J]. Transportation Research Part C: Emerging Technologies, 2021, 132: 103372. doi: 10.1016/j.trc.2021.103372 [85] 王庆荣, 慕壮壮, 朱昌锋, 等. 基于HDNNF-CAF的短时交通流预测研究[J]. 计算机工程与应用, 2025, 61(15): 318-328.WANG Qing-rong, MU Zhuang-zhuang, ZHU Chang-feng, et al. Research on short-term traffic flow prediction based on HDNNF-CAF[J]. Computer Engineering and Applications, 2025, 2025, 61 (15): 318-328. [86] 刘思林, 廖祝华, 符琦, 等. 多影响因素下的交通流速度预测[J]. 湖南科技大学学报(自然科学版), 2024, 39(3): 109-115.LIU Si-lin, LIAO Zhu-hua, FU Qi, et al. Prediction of traffic flow speed under multiple influencing factors[J]. Journal of Hunan University of Science & Technology (Natural Science Edition), 2024, 39(3): 109-115. [87] 寇敏, 张萌萌, 赵军学, 等. 融合天气特征的WOA-GRU高速公路短时交通流预测[J]. 公路, 2024, 69(4): 193-199.KOU Min, ZHANG Meng-meng, ZHAO Jun-xue, et al. WOA-GRU expressway short-term traffic flow prediction incorporating weather features[J]. Highway, 2024, 69(4): 193-199. [88] 胡春华, 曾萼岚, 荣辉桂. 基于双图卷积机制的数字孪生交通流预测[J]. 电子学报, 2025, 53(1): 141-150.HU Chun-hua, ZENG E-lan, RONG Hui-gui. Traffic flow prediction of digital twin based on two-graph convolution mechanism[J]. Acta Electronica Sinica, 2025, 53(1): 141-150. [89] LIU C, YANG S, XU Q, et al. Spatial-temporal large language model for traffic prediction[C]//IEEE. 2024 25th IEEE International Conference on Mobile Data Management (MDM). New York: IEEE, 2024: 31-40. -
图(3) / 表(3)
计量
- 文章访问数: 18
- HTML全文浏览量: 6
- PDF下载量: 1
- 被引次数: 0
