-
摘要: 通过文献梳理、专家访谈和试验场景构建等方法，分析了道路指定断面和区域路网宏观交通流预测的国内外研究现状和发展趋势，归纳了局部断面交通流预测方法，包括传统机器学习、递归神经网络和混合模型，分析了卷积神经网络、图神经网络和融合多因素网络的特点，阐述了方法的原理、优势、局限性和应用场景，总结了现有场景交通数据集类别，从采样周期与采集方式角度归纳了国内外主流交通数据集。分析结果表明：递归神经网络可以有效获取交通数据的历史规律，但存在梯度爆炸、计算复杂度高、长时预测准确度不佳等问题；图神经网络针对路网拓扑连接关系引入了图结构，在考虑路网和交通流数据的时空相关性上具有明显优势；融合多因素网络充分考虑天气、道路、事故等内外部因素的影响，有效提升了交通流预测的实时性和鲁棒性；由于交通数据采集困难、外部因素影响难以量化、机器学习方法可解释性差等原因，交通流预测方法的改进受到了限制；未来应从交通信息有效挖掘和图卷积方法完善两方面入手，拓宽图结构在交通领域的应用和考虑非常态交通场景，进一步揭示交通数据的内在规律，开发更准确、高效的交通流预测方法，推动交通流预测在工业界的落地应用。Abstract: The research status and development trend of macro traffic flow prediction of designated road sections and regional road network at home and abroad were analyzed by literature review, expert interview, and experimental scenario construction. Local section traffic flow prediction methods were summarized, including traditional machine learning, recurrent neural networks, and hybrid models. The characteristics of convolutional neural networks, graph neural networks, and fusion multi-factor networks were discussed.The principles, advantages, limitations, and application scenarios of the methods were explained. The types of existing scenario traffic datasets and the mainstream traffic datasets at home and abroad were summarized from the perspectives of sampling periods and collecting methods. Analysis results show that recurrent neural networks can effectively obtain the historical laws of traffic data, but there are some problems such as gradient explosion, high computational complexity, and poor accuracy of long-time prediction. Graph neural networks introduce graph structures for road network topological connection relationships, which has obvious advantage in considering the spatiotemporal correlation of road network and traffic flow data. Fusion multi-factor methods fully consider the influence of internal and external factors such as weather, roads, and accidents, effectively improving the real-time performance and robustness of traffic flow prediction. The improvements of traffic flow prediction methods have limitations due to the difficult traffic data collection and external factor influence quantification, as well as the poor interpretability of machine learning methods. The future research should start from two aspects of starting the efficient mining of traffic information and the perfection of graph convolution methods, broaden the application of graph structures in the traffic field, and consider non-constant traffic scenarios. So as to further reveal the inherent laws of traffic data, develop more accurate and efficient traffic flow prediction methods, and promote the application of traffic flow prediction in industry.
-
图 1 陕西省西安市某指定断面交通流
Figure 1. Traffic flow at a designated section in Xi'an Shaanxi Province
图 2 K-NN方法内部数据流传递关系
Figure 2. Transfer relationship of internal data flow in K-NN method
图 5 基于递归神经网络的交通流预测主流方法
Figure 5. Mainstream methods of traffic flow prediction based on recurrent neural network
图 15 陕西省186个收费站点交通流数据
Figure 15. Traffic flow data of 186 toll stations in Shaanxi Province
表 1 三种断面交通流预测方法对比
Table 1. Comparison of three section traffic flow prediction methods
方法 原理 局限性 适用场景 传统机器学习 训练使用统计学知识和交通特征建立的回归方法 体系结构较浅，适用范围极其有限, 必须手动选取特征 预测时间短、精度需求低、数据量小的单一场景 递归神经网络 借助记忆单元学习历史数据对当前的影响 长时依赖性获取不足，训练成本高 精度需求高与数据量大的单一场景 混合模型 衔接几种方法或并行计算多个方法 未充分考虑路网的空间特性，计算复杂度高 预测精度和时间要求高的复杂场景 
下载: 导出CSV
表 2 十种典型方法的试验结果对比
Table 2. Experimental result comparison of 10 typical methods
方法 平均绝对误差 平均绝对离差 均方根误差 训练时间/min 时序图卷积网络
(Temporal Graph Convolutional Network，T-GCN)2.915/3.154
3.429 /3.6800.709/0.711
0.723/0.7288.532/9.019
9.608 /10.129120 STGCN 3.124/3.467
3.826/4.1740.828/0.862
0.831 /0.8539.199/10.371
11.706/12.92322 DCRNN 4.130/5.120
6.430 /7.5260.964/1.120
1.428/1.6349.650/10.620
11.882 /12.949160 时间卷积网络
(Temporal Convolutional Network, TCN)5.372/9.305
14.575 /18.9533.280/5.859
10.040/13.1539.664/12.520
19.574 /23.82964 GRU 6.547/10.130
16.570/21.1053.586/6.847
11.544 /15.2839.981/15.328
25.114/31.94178 SAE 7.625/11.985
16.980 /21.5513.626/5.897
10.662/13.76410.136/15.525
25.744 /32.74388 LSTM 7.727/12.232
17.246/21.9213.370/5.920
10.626 /13.89410.332/16.354
26.288/33.61496 支持向量回归
(Support Vector Regression，SVR)6.705/11.406
22.808 /20.7433.923/6.478
15.186/19.79220.017/34.670
67.055 /87.619130 ARIMA 12.094/22.913
43.934/58.1537.605/14.742
30.161 /40.05816.961/31.009
57.026/75.063210 历史平均
(Historical Average, HA)14.602/26.620
45.830 /60.2453.751/7.000
12.583/16.6136.309/64.627
108.666/142.22190
下载: 导出CSV
表 3 三种区域交通流预测方法对比
Table 3. Comparison of three regional traffic flow prediction methods
方法 原理 优势 局限性 适用场景 后续应用 卷积神经网络 采用2个连续的卷积层和池化层提取路网空间信息 局部连接性，输出神经元只连接到附近的局部输入神经元；池化机制，很大程度上减少了训练CNN所需的参数数量，同时保证了最重要的特征被保留；全连接性，应用于最后阶段的全连接层使得输入层的数据维度是可控的 在具有非欧几里得拓扑的运输网络中具有局限性 路网结构较为简单的场景 交通态势评估、通行能力分析与收费站人力规划 图神经网络 利用图神经网络来建模交通网络中的空间依赖性，再利用卷积从根本上提高图分析效率 空间解释性好；图结构的引入有效地捕获了非欧结构的路网特性 未考虑天气等其他因素对路网的影响 路网结构复杂、外部因素影响弱的场景 交通信号协调控制与地铁车辆调度 融合多因素 利用多源数据并将外部影响因素整合到方法中 实用性高；考虑外部因素对交通状况的影响 相关性因素的融合仍不够成熟 外部因素对交通状况影响较大的场景 交通事故分析
下载: 导出CSV
表 4 交通预测公开数据集
Table 4. Public datasets for traffic prediction
分类 数据集名称 采样周期 采集方式 固定式采集数据集 交通性能测量系统数据集 5 min 车辆检测器 多尺度时空交通估计与预测数据集 5 min 车辆检测器 洛杉矶高速公路数据集 5 min 环形检测器 西雅图城市交通流数据集 5 min 地感线圈 纽约市自行车共享行程数据集 自行车数据 上海地铁客流数据集、深圳地铁客流数据集 15 min 地铁站点 移动式采集数据集 马德里城市交通追踪数据集 0.5 s 车辆轨迹采集 纽约市出租车和豪华轿车委员会行程数据集 出租车记录 北京市出租车GPS轨迹数据集 30 min GPS数据 上海市交通行程时间及车速数据集 10 min 出租车记录 深圳市浮动车数据集 15 min 出租车轨迹 北京市出租车GPS轨迹数据集 出租车轨迹 滴滴出行交通流量预测数据集 网约车记录 科隆市的推特交通信息语料库 1 s 车辆轨迹采集 弗吉尼亚理工大学自然驾驶研究数据集 1 s 车辆轨迹采集
下载: 导出CSV
-
[1] WANG Yi-bing, YU Xiang-hua, ZHANG Si-yu, et al. Freeway traffic control in presence of capacity drop[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1497-1516. doi: 10.1109/TITS.2020.2971663 [2] 曾筠程, 邵敏华, 孙立军, 等. 基于有向图卷积神经网络的交通预测与拥堵管控[J]. 中国公路学报, 2021, 34(12): 239-248. doi: 10.3969/j.issn.1001-7372.2021.12.018ZENG Yun-cheng, SHAO Min-hua, SUN Li-jun, et al. Traffic prediction and congestion control based on directed graph convolution neural network[J]. China Journal of Highway and Transport, 2021, 34(12): 239-248. (in Chinese) doi: 10.3969/j.issn.1001-7372.2021.12.018 [3] 张伟斌, 张帅, 郭海锋, 等. 基于交通因子状态网络的城市交叉口交通流预测[J]. 中国公路学报, 2021, 34(12): 217-228. doi: 10.3969/j.issn.1001-7372.2021.12.016ZHANG Wei-bin, ZHANG Shuai, GUO Hai-feng, et al. Traffic flow prediction of urban intersections based on a traffic factor state network[J]. China Journal of Highway and Transport, 2021, 34(12): 217-228. (in Chinese) doi: 10.3969/j.issn.1001-7372.2021.12.016 [4] SHI Xiao-ming, QI Heng, SHEN Yan-ming, et al. A spatial- temporal attention approach for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(8): 4909-4918. doi: 10.1109/TITS.2020.2983651 [5] 宋国杰, 胡程, 谢昆青, 等. 面向实时短时交通流预测的过程神经元网络建模[J]. 交通运输工程学报, 2009, 9(5): 73-77. doi: 10.3321/j.issn:1671-1637.2009.05.013SONG Guo-jie, HU Cheng, XIE Kun-qing, et al. Process neural network modeling for real-time short-term traffic flow prediction[J]. Journal of Traffic and Transportation Engineering, 2009, 9(5): 73-77. (in Chinese) doi: 10.3321/j.issn:1671-1637.2009.05.013 [6] 马永杰, 程时升, 马芸婷, 等. 卷积神经网络及其在智能交通系统中的应用综述[J]. 交通运输工程学报, 2021, 21(4): 48-71. doi: 10.19818/j.cnki.1671-1637.2021.04.003MA Yong-jie, CHENG Shi-sheng, MA Yun-ting, et al. Review of convolutional neural network and its application in intelligent transportation system[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 48-71. (in Chinese) doi: 10.19818/j.cnki.1671-1637.2021.04.003 [7] 《中国公路学报》编辑部. 中国交通工程学术研究综述·2016[J]. 中国公路学报, 2016, 29(6): 1-161. doi: 10.3969/j.issn.1001-7372.2016.06.001Editorial Department of China Journal of Highway and Transport. Review on China's Traffic engineering research progress· 2016[J]. China Journal of Highway and Transport, 2016, 29(6): 1-161. (in Chinese) doi: 10.3969/j.issn.1001-7372.2016.06.001 [8] 陈俊杰, 上官伟, 蔡伯根, 等. 交通流特征深度认知的车队运行参数优化方法[J]. 中国公路学报, 2020, 33(11): 264-274. doi: 10.3969/j.issn.1001-7372.2020.11.025CHEN Jun-jie, SHANGGUAN Wei, CAI Bai-gen, et al. Platoon operating-parameter optimization method based on deep cognition of traffic-flow features[J]. China Journal of Highway and Transport, 2020, 33(11): 264-274. (in Chinese) doi: 10.3969/j.issn.1001-7372.2020.11.025 [9] LI Wen-gen, CAO Jian-nong, GUAN Ji-hong, et al. A general framework for unmet demand prediction in on-demand transport services[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(8): 2820-2830. doi: 10.1109/TITS.2018.2873092 [10] LIN Lu, LI Jian-xin, CHEN Feng, et al. Road traffic speed prediction: a probabilistic model fusing multi-source data[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(7): 1310-1323. doi: 10.1109/TKDE.2017.2718525 [11] GONG Yong-shun, LI Zhi-bin, ZHANG Jian, et al. Network-wide crowd flow prediction of Sydney trains via customized online non-negative matrix factorization[C]//ACM. Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018: 1243-1252. [12] COVER T, HART P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1): 21-27. doi: 10.1109/TIT.1967.1053964 [13] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297. [14] PEARL J. Probabilistic reasoning in intelligent systems: networks of plausible inference[J]. Artificial Intelligence, 1991, 48(1): 117-124. doi: 10.1016/0004-3702(91)90084-W [15] GONG Xiao-yan, WANG Fei-yue. Three improvements on KNN-NPR for traffic flow forecasting[C]//IEEE. The IEEE 5th International Conference on Intelligent Transportation Systems. New York: IEEE, 2003: 736-740. [16] TONG Jian-cheng, GU Xiang, ZHANG Miao, et al. Traffic flow prediction based on improved SVR for VANET[C]//IEEE. 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering(AEMCSE). New York: IEEE, 2021: 402-405. [17] SUN Shi-liang, ZHANG Chang-shui, YU Guo-qiang. A bayesian network approach to traffic flow forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7(1): 124-132. doi: 10.1109/TITS.2006.869623 [18] ALEXANDER TEDJOPURNOMO D, BAO Zhi-feng, ZHENG Bai-hua, et al. A survey on modern deep neural network for traffic prediction: trends, methods and challenges[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(4): 1544-1561. [19] DOUGHERTY M. A review of neural networks applied to transport[J]. Transportation Research Part C: Emerging Technologies, 1995, 3(4): 247-260. doi: 10.1016/0968-090X(95)00009-8 [20] VYTHOULKAS P. Alternative approaches to short term traffic forecasting for use in driver information systems[J]. Transportation and Traffic Theory, 1993, 12: 485-506. [21] HUA Jiu-yi, FAGHRI A. Applications of artificial neural networks to intelligent vehicle-highway systems[J]. Transportation Research Record, 1994, 1453: 83-90. [22] WU Qing, JIANG Zhe, HONG Ke-wei, et al. Tensor-based recurrent neural network and multi-modal prediction with its applications in traffic network management[J]. IEEE Transactions on Network and Service Management, 2021, 18(1): 780-792. doi: 10.1109/TNSM.2021.3056912 [23] DU Yi, CUI Na-xin, LI Hui-Xin, et al. The vehicle's velocity prediction methods based on RNN and LSTM neural network[C]//IEEE. Proceedings of 2020 Chinese Control and Decision Conference(CCDC). New York: IEEE, 2020: 99-102. [24] MA Xiao-lei, TAO Zhi-min, WANG Yin-hai, 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 [25] CHUNG J Y, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. ArXiv Preprint, 2014, DOI: arXiv:1412.3555 .[26] FU Rui, ZHANG Zuo, LI Li, et al. Using LSTM and GRU neural network methods for traffic flow prediction[C]//IEEE. 31st Youth Academic Annual Conference of Chinese Association of Automation. New York: IEEE, 2016: 324-328. [27] ZHAO Zheng, CHEN Wei-hai, WU Xing-ming, et al. LSTM network: a deep learning approach for short-term traffic forecast[J]. IET Intelligent Transport Systems. 2017, 11(2): 68-75. doi: 10.1049/iet-its.2016.0208 [28] ZHU Ling-xue, LAPTEV N. Deep and confident prediction for time series at uber[C]//IEEE. 2017 IEEE International Conference on Data Mining Workshops (ICDMW). New York: IEEE, 2017: 103-110. [29] TIAN Yan, ZHANG Kai-li, LI Jian-yuan, et al. LSTM-based traffic flow prediction with missing data[J]. Neurocomputing, 2018, 318: 297-305. doi: 10.1016/j.neucom.2018.08.067 [30] PAN Zhe-yi, LIANG Yu-xuan, WANG Wei-feng, et al. Urban traffic prediction from spatio-temporal data using deep meta learning[C]//ACM. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 1720-1730. [31] DESHPANDE P, SARAWAGI S. Streaming adaptation of deep forecasting models using adaptive recurrent units[C]//ACM. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 1560-1568. [32] YANG Bai-lin, SUN Shu-lin, LI Jian-yuan, et al. Traffic flow prediction using LSTM with feature enhancement[J]. Neurocomputing, 2019, 332: 320-327. doi: 10.1016/j.neucom.2018.12.016 [33] 谭满春, 冯荦斌, 徐建闽, 等. 基于ARIMA与人工神经网络组合模型的交通流预测[J]. 中国公路学报, 2007, 20(4): 118-121. doi: 10.3321/j.issn:1001-7372.2007.04.021TAN Man-chun, FENG Nao-bin, XU Jian-min, et al. Traffic flow prediction based on hybrid ARIMA and ANN model[J]. China Journal of Highway and Transport, 2007, 20(4): 118-121. (in Chinese) doi: 10.3321/j.issn:1001-7372.2007.04.021 [34] TIAN Yin, WEI Chen-chen, XU Dong-wei, et al. Traffic flow prediction based on stack autoencoder and long short-term memory network[C]//IEEE. 2020 IEEE 3rd International Conference on Automation, Electronics and Electrical Engineering (AUTEEE). New York: IEEE, 2020: 385-388. [35] LI Ya-guang, SHAHABI C. A brief overview of machine learning methods for short-term traffic forecasting and future directions[J]. SIGSPATIAL Special, 2018, 10(1): 3-9. doi: 10.1145/3231541.3231544 [36] MA Xiao-lei, DAI Zhuang, HE Zheng-bing, et al. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): 818. doi: 10.3390/s17040818 [37] CAO Xiao-fang, ZHONG Yu-hua, ZHOU Yun, et al. Interactive temporal recurrent convolution network for traffic prediction in data centers[J]. IEEE Access, 2017, 6: 5276-5289. [38] GUO Shen-nan, LIN You-fang, LI Shi-jie, et al. Deep spatial- temporal 3D convolutional neural networks for traffic data forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(10): 3913-3926. doi: 10.1109/TITS.2019.2906365 [39] YAO Hua-xiu, TANG Xian-feng, WEI Hua, et al. Revisiting spatial-temporal similarity: a deep learning framework for traffic prediction[C]//AAAI. Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019: 5668-5675. [40] WU Yuan-kai, TAN Hua-chun. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework[J]. ArXiv Preprint, 2016, DOI: arXiv:1612.01022 .[41] ZHANG Jun-bo, ZHENG Yu, QI De-kang, et al. DNN-based prediction model for spatio-temporal data[C]//ACM. Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York: ACM, 2016: 1-4. [42] YAO Hua-xin, WU Fei, KE Jin-tao, et al. Deep multi-view spatial-temporal network for taxi demand prediction[C]//AAAI. Proceedings of the 32nd AAAI conference on artificial intelligence. Palo Alto: AAAI, 2018: 2588-2595. [43] WANG Dong, ZHANG Jun-bao, CAO Wei, et a. When will you arrive? Estimating travel time based on deep neural networks[C]//AAAI. Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2018: 2500-2507. [44] LIN Zi-qian, FENG Jie, LU Zi-yang, et al. DeepSTN+: context-aware spatial-temporal neural network for crowd flow prediction in metropolis[C]//AAAI. Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019: 1020-1027. [45] ZHAO Jun-hui, ZHU Tian-qi, ZHAO Rui-dong, et al. Layerwise recurrent autoencoder for real-world traffic flow forecasting[C]//Springer. Proceedings of 9th International Conference on Intelligence Science and Big Data Engineering. Berlin: Springer, 2019: 78-88. [46] LYU Zhong-jian, XU Jia-jie, ZHENG Kai, et al. LC-RNN: a deep learning model for traffic speed prediction[C]//IJCAI. Proceedings of the 27th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2018: 3470-3476. [47] LAI Guo-kun, CHANG Wei-cheng, YANG Yi-ming, et al. Modeling long-and short-term temporal patterns with deep neural networks[C]//ACM. Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2018: 95-104. [48] ZONOOZI A, KIM J J, LI Xiao-li, et al. Periodic-CRN: a convolutional recurrent model for crowd density prediction with recurring periodic patterns[C]//IJCAI. Proceedings of the 27th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2018: 3732-3738. [49] KE Jin-tao, ZHENG Hong-yu, YANG Hai, et al. Short- term forecasting of passenger demand under on-demand ride services: a spatio-temporal deep learning approach[J]. Transportation Research Part C: Emerging Technologies, 2017, 85: 591-608. doi: 10.1016/j.trc.2017.10.016 [50] WANG Le-ye, GENG Xu, MA Xiao-juan, et al. Cross-city transfer learning for deep spatio-temporal prediction[C]//IJCAI. Proceedings of the 28th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2019: 1893-1899. [51] ZANG Di, LING Jia-wei, WEI Zhi-hua, et al. Long-term traffic speed prediction based on multiscale spatio-temporal feature learning network[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(10): 3700-3709. [52] YE Jun-chen, SUN Lei-lei, DU Bo-wen, et al. Co-prediction of multiple transportation demands based on deep spatio-temporal neural network[C]//ACM. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 305-313. [53] JIANG Ren-he, SONG Xuan, HUANG Dou, et al. Deep urban event: a system for predicting citywide crowd dynamics at big events[C]//ACM. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 2114-2122. [54] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//NIPS. 30th Conference on Neural Information Processing Systems. San Diego: NIPS, 2016: 3844-3852. [55] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//ICLR. The 2017 International Conference on Learning Representations. New York: ICLR, 2017: 1-14. [56] XU Bing-bing, SHEN Hua-wei, CAO Qi, et al. Graph wavelet neural network[C]//ICLR. 7th International Conference on Learning Representations. New York: ICLR, 2019: 1-13. [57] NIEPERT M, AHMED M, KUTZKOV K. Learning convolutional neural networks for graphs[C]//ICML. Proceedings of the 33rd International Conference on Machine Learning. New York: ICML, 2016: 2014-2023. [58] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C]//NIPS. 31st Conference on Neural Information Processing Systems. San Diego: NIPS, 2017: 1-11. [59] VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//ICLR. Proceedings of the 6th International Conference on Learning Representations. New York: ICLR, 2018: 1-12. [60] MONTI F, BOSCAINI D, MASCI J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs[C]// IEEE. 2017 Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2017: 5425-5434. [61] XU Bing-bing, SHEN Hua-wei, CAO Qi, et al. Graph convolutional networks using heat kernel for semi-supervised learning[C]//IJCAI. Proceedings of the 28th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2019: 1928-1934. [62] SEO Y, DEFFERRARDM, VANDERGHEYNST P, et al. Structured sequence modeling with graph convolutional recurrent networks[C]//Springer. Proceedings of the 25th International Conference on Neural Information Processing (ICONIP). Berlin: Springer, 2018: 362-373. [63] LI Ya-guang, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[C]//ICLR. Proceedings of the 6th International Conference on Learning Representations. New York: ICLR, 2018: 1-16. [64] WU Zong-han, PAN Shi-rui, LONG Guo-dong, et al. Graph wavenet for deep spatial-temporal graph modeling[C]//IJCAI. Proceedings of the 28th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2019: 1907-1913. [65] YU Bing, YIN Hao-teng, ZHU Zhan-xing. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//IJCAI. Proceedings of the 27th International Joint Conference on Artificial Intelligence. Freiburg: IJCAI, 2018: 3634-3640. [66] GUO Sheng-nan, LIN You-fang, FENG Ning, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//AAAI. Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020: 922-929. [67] ZHENG Chuan-pan, FAN Xiao-liang, WANG Cheng, et al. GMAN: a graph multi-attention network for traffic prediction[C]// AAAI. Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020: 1234-1241. [68] WANG Xiao-yang, MA Yao, WANG Yi-qi, et al. Traffic flow prediction via spatial temporal graph neural network[C]// ACM. Proceedings of the 29th World Wide Web Conference (WWW). New York: ACM, 2020: 1082-1092. [69] CHEN Wei-qi, CHEN Ling, XIE Yu, et al. Multi-Range attentive bicomponent graph convolutional network for traffic forecasting[C]//AAAI. Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020: 3529-3536. [70] CHEN Cen, LI Ken-li, TEO S G, et al. Gated residual recurrent graph neural networks for traffic prediction[C]//AAAI. Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019: 485-492. [71] LI Meng-zhang, ZHU Zhan-xing. Spatial-temporal fusion graph neural networks for traffic flow forecasting[C]//AAAI. Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2021: 4189-4196. [72] LYU Ming-qi, HONG Zhao-xiong, CHEN Ling, et al. Temporal multi-graph convolutional network for traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6): 3337-3348. doi: 10.1109/TITS.2020.2983763 [73] ZHANG Yang, CHENG Tao, REN Yi-bin, et al. A novel residual graph convolution deep learning model for short-term network-based traffic forecasting[J]. International Journal of Geographical Information Science, 2020, 34(5): 969-995. doi: 10.1080/13658816.2019.1697879 [74] MALLICK T, BALAPRAKASH P, RASK E, et al. Graph-partitioning-based diffusion convolutional recurrent neural network for large-scale traffic forecasting[J]. Transportation Research Record, 2020, 2674(9): 473-488. doi: 10.1177/0361198120930010 [75] LI Zhi-shuai, XIONG Gang, TIAN Yong-lin, et al. A multi-stream feature fusion approach for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(2): 1456-1466. doi: 10.1109/TITS.2020.3026836 [76] LIU Jie-lun, ONG P, CHEN Xi-qun. Graph SAGE-based traffic speed forecasting for segment network with sparse data[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(3): 1755-1766. doi: 10.1109/TITS.2020.3026025 [77] OH S D, KIM Y J, HONG Ji-sun. Urban traffic flow prediction system using a multifactor pattern recognition model[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(5): 2744-2755. doi: 10.1109/TITS.2015.2419614 [78] ZHENG Chuan-pan, FAN Xiao-liang, WEN Cheng-lu, et al. DeepSTD: mining spatio-temporal disturbances of multiple context factors for citywide traffic flow prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3744-3755. doi: 10.1109/TITS.2019.2932785 [79] HE Kai-ming, ZHANG Xiang-yu, REN Shao-qing, et al. Identity mappings in deep residual networks[C]//Springer. Proceedings of the 14th European Conference on Computer Vision (ECCV). Berlin: Springer, 2016: 630-645. [80] LIAO Bin-bing, ZHANG Jing-qing, WU Chao, et al. Deep sequence learning with auxiliary information for traffic prediction[C]//ACM. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2018: 537-546. [81] ZHANG Jun-bo, ZHENG Yu, QI De-kang, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Artificial Intelligence, 2018, 259: 147-166. doi: 10.1016/j.artint.2018.03.002 [82] WANG Ping, ZHANG Ya-jie, WANG Sai-sai, et al. Forecasting travel speed in the rainfall days to develop suitable variable speed limits control strategy for less driving risk[J]. Journal of Advanced Transportation, 2021, 2021: 1-13. [83] ZHANG Jun-bo, ZHENG Yu, QI De-kang. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]// AAAI. Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2017: 1655-1661. [84] WANG Ping, XU Wan-rong, JIN Yin-li, et al. Forecasting traffic volume at a designated cross-section location on a freeway from large-regional toll collection data[J]. IEEE Access, 2019, 7: 9057-9070. doi: 10.1109/ACCESS.2018.2890725 [85] WANG Ping, HAO Wen-bang, JIN Yin-li, et al. Fine-grained traffic flow prediction of various vehicle types via fusion of multisource data and deep learning approaches[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 6921-6930. doi: 10.1109/TITS.2020.2997412 [86] 赵海龙, 张干, 吕安涛, 等. 基于EMD-Wavelet模型的实时交通流噪声数据清洗方法[J]. 交通科技, 2013(2): 150-153. https://www.cnki.com.cn/Article/CJFDTOTAL-SKQB201302051.htmZHAO Hai-long, ZHANG Gan, LYU An-tao, et al. Research on noise reduction of real-time traffic data based on emd-wavelet model[J]. Transportation Science and Technology, 2013(2): 150-153. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SKQB201302051.htm [87] QU Li, ZHANG Yi, HU Jian-ming, et al. A BPCA based missing value imputing method for traffic flow volume data[C]// IEEE. Proceedings of IEEE Intelligent Vehicles Symposium. New York: IEEE, 2008: 985-990. [88] QU Li, LI li, ZHANG Yi, et al. PPCA-based missing data imputation for traffic flow volume: a systematical approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2009, 10(3): 512-522. doi: 10.1109/TITS.2009.2026312 [89] 侯思安, 张峰, 李向阳. 基于贝叶斯概率矩阵分解的地震数据重建算法[J]. 石油科学通报, 2018, 3(2): 154-166. https://www.cnki.com.cn/Article/CJFDTOTAL-SYKE201802004.htmHOU Si-an, ZHANG Feng, LI Xiang-yang. Seismic data reconstruction via a Bayesian probabilistic matrix factorization algorithm[J]. Petroleum Science Bulletin, 2018, 3(2): 154-166. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SYKE201802004.htm [90] TAN Hua-chun, FENG Guang-dong, FENG Jian-shuai, et al. A tensor-based method for missing traffic data completion[J]. Transportation Research Part C: Emerging Technologies, 2013, 28: 15-27. doi: 10.1016/j.trc.2012.12.007 [91] ACAR E, DUNLAVY D M, KOLDA T G, et al. Scalable tensor factorizations for incomplete data[J]. Chemometrics and Intelligent Laboratory Systems, 2011, 106(1): 41-56. doi: 10.1016/j.chemolab.2010.08.004 [92] CHEN Yi-lei, HSU C T, LIAO H Y M. Simultaneous tensor decomposition and completion using factor priors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(3): 577-591. doi: 10.1109/TPAMI.2013.164 [93] LIU Ji, 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 [94] SU Ya-ru, WU Xiao-hui, LIU Wen-xi. Low-rank tensor completion by sum of tensor nuclear norm minimization[J]. IEEE Access, 2019, 7: 134943-134953. doi: 10.1109/ACCESS.2019.2940664 [95] 徐程, 曲昭伟, 陶鹏飞, 等. 动态交通数据异常值的实时筛选与恢复方法[J]. 哈尔滨工程大学学报, 2016, 37(2): 211-217. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBG201602012.htmXU Cheng, QU Zhao-wei, TAO Peng-fei, et al. Methods of real-time screening and reconstruction for dynamic traffic abnormal data[J]. Journal of Harbin Engineering University, 2016, 37(2): 211-217. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HEBG201602012.htm [96] 裴莉莉, 孙朝云, 韩雨希, 等. 基于SSC与XGBoost的高速公路异常收费数据修复算法[J]. 吉林大学学报(工学版), 2022, 52(10): 2325-2332. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY202210013.htmPEI Li-li, SUN Zhao-yun, HAN Yu-xi, et al. Algorithm for repairing abnormal toll data of expressway based on SSC and XGBoost[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(10): 2325-2332. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY202210013.htm [97] 阮嘉琨, 蔡延光, 乐冰. 基于DBSCAN密度聚类算法的高速公路交通流异常数据检测[J]. 工业控制计算机, 2019, 32(7): 92-94. https://www.cnki.com.cn/Article/CJFDTOTAL-GYKJ201907039.htmRUAN Jia-kun, CAI Yan-guang, LE Bing. Highway traffic flow anomaly data detection based on DBSCAN density clustering algorithm[J]. Industrial Control Computer, 2019, 32(7): 92-94. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GYKJ201907039.htm [98] 周博, 贾树林, 胡江宇, 等. 基于机器学习的交通流参数异常数据处理模型研究[J]. 武汉纺织大学学报, 2021, 34(2): 9-14. https://www.cnki.com.cn/Article/CJFDTOTAL-WFGB202102003.htmZHOU Bo, JIA Shu-lin, HU Jiang-yu, et al. Research on data processing model of traffic flow parameter anomaly based on machine learning[J]. Journal of Wuhan Textile University, 2021, 34(2): 9-14. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-WFGB202102003.htm [99] 秦一菲, 马明辉, 王岩松, 等. 基于改进KNN方法的交通流异常数据修复算法[J]. 计算机测量与控制, 2018, 26(12): 180-184. https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201812041.htmQIN Yi-fei, MA Ming-hui, WANG Yan-song, et al. A recovery method for abnormal traffic flow data based on improved knn algorithm[J]. Computer Measurement and Control, 2018, 26(12): 180-184. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201812041.htm [100] 秦胜君, 李婷. 一种基于长短记忆模型的交通轨迹异常挖掘模型[J]. 广西科技大学学报, 2021, 32(2): 58-64. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGX202102010.htmQIN Sheng-jun, LI Ting. An anomaly detection algorithm for traffic trajectory data based on long short term memory model[J]. Journal of Guangxi University of Science and Technology, 2021, 32(2): 58-64. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GXGX202102010.htm [101] ZHU Li, YU F R, WANG Yi-ge, et al. Big data analytics in intelligent transportation systems: a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(1): 383-398. [102] BUI K H N, CHO J, YI H. Spatial-temporal graph neural network for traffic forecasting: an overview and open research issues[J]. Applied Intelligence, 2022, 52(3): 2763-2774. [103] CAO Zhi-guang, JIANG Si-wei, ZHANG Jie, et al. A unified framework for vehicle rerouting and traffic light control to reduce traffic congestion[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(7): 1958-1973. [104] QI Liang, ZHOU Meng-chu, LUAN Wen-jing. A two-level traffic light control strategy for preventing incident-based urban traffic congestion[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 19(1): 13-24. [105] LI Hui, WANG Peng, SHEN Chun-hua. Toward end-to-end car license plate detection and recognition with deep neural networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(3): 1126-1136. [106] YUAN Wu-bei, WANG Ping, YANG Jing-wen, et al. An alternative reliability method to evaluate the regional traffic congestion from GPS data obtained from floating cars[J]. IET Smart Cities, 2021, 3(2): 79-90. [107] JIN Yin-li, JIA Zhen, WANG Ping, et al. Quantitative assessment on truck-related road risk for the safety control via truck flow estimation of various types[J]. IEEE Access, 2019, 7: 88799-88810. [108] JIN Yin-li, GAO Yi-wen, WANG Ping, et al. Improved manpower planning based on traffic flow forecast using a historical queuing model[J]. IEEE Access, 2019, 7: 125101-125112. -
点击查看大图
图(18) / 表(4)
计量
- 文章访问数: 4049
- HTML全文浏览量: 507
- PDF下载量: 820
- 被引次数: 0
