一种城市出行需求预测的时空方法
A Spatio-Temporal Approach for Urban Travel Demand Forecasting
DOI: 10.12677/CSA.2023.133051, PDF,    国家自然科学基金支持
作者: 楚本嘉, 马照斌：青岛大学计算机科学技术学院，山东 青岛；李建波*：青岛大学计算机科学技术学院，山东 青岛;青岛大学泛在网络与城市计算研究所，山东 青岛；刘 阳, 夏丰千：青岛大学泛在网络与城市计算研究所，山东 青岛
关键词: 深度学习；城市出行需求；预测；Deep Learning； Urban Travel Demand； Forecasting
摘要: 预测城市出行需求对于交通管理、保障公共出行安全和建设智慧城市具有重要意义。然而，由于受区域间交通状况、天气、节假日等诸多复杂因素的影响，城市出行需求数据往往存在高频噪声和复杂的波动模式。本文提出了一种基于深度学习的城市出行需求预测模型(Spatio-Temporal Urban Travel Demand Forecasting Model, STUTDFM)。该模型的架构由外部因素影响组件、时空特征提取组件和数据融合组件组成。外部因素影响组件可以处理城市出行需求影响因素的数据，从而拟合一些局部极值，时空特征提取组件可以捕获城市出行需求数据的空间依赖性和时间依赖性，数据融合组件可以将外部因素影响组件和时空特征提取组件调整到整体预测模型中。对四个真实数据集的实验表明，所提出的城市出行需求预测模型方法优于八种众所周知的方法。
Abstract: Predicting urban travel demand is of great significance for traffic management, ensuring public travel safety and building smart cities. However, due to the influence of many complex factors such as inter-regional traffic conditions, weather and holidays, urban travel demand data often has high frequency noise and complex fluctuation patterns. This paper proposes a deep learning-based urban travel demand prediction model—Spatio-Temporal Urban Travel Demand Forecasting Model (STUTDFM). The architecture of the model consists of an external factor influence component, a spatio-temporal feature extraction component and a data fusion component. EIFC can process the data of the factors affecting urban travel demand so as to fit some local extremes, SPFEC can capture the spatial dependence and temporal dependence of urban travel demand data, and DFC can adjust EIFC and STFEC to the overall prediction model. Experiments on four real datasets show that the proposed STUTDF method outperforms eight well-known methods.
文章引用：楚本嘉, 李建波, 刘阳, 马照斌, 夏丰千. 一种城市出行需求预测的时空方法[J]. 计算机科学与应用, 2023, 13(3): 518-527. https://doi.org/10.12677/CSA.2023.133051

参考文献

[1] Lv, Z., Li, J., Dong, C., Li, H. and Xu, Z. (2021) Deep Learning in the COVID-19 Epidemic: A Deep Model for Urban Traffic Revitalization Index. Data & Knowledge Engineering, 135, Article ID: 101912. [Google Scholar] [CrossRef] [PubMed]
[2] Lv, Z., Li, J., Li, H., Xu, Z. and Wang, Y. (2021) Blind Travel Prediction Based on Obstacle Avoidance in Indoor Scene. Wireless Communications and Mobile Computing, 2021, Ar-ticle ID: 5536386. [Google Scholar] [CrossRef] 
[3] Sun, H., Lv, Z., Li, J., Xu, Z., Sheng, Z. and Ma, Z. (2022) Prediction of Cancellation Probability of Online Car-Hailing Orders Based on Multi-Source Heterogeneous Data Fusion. Wireless Algorithms, Systems, and Applications: 17th International Conference, WASA 2022, Dalian, 24-26 November 2022, 168-180. [Google Scholar] [CrossRef] 
[4] Lv, Z., Li, J., Dong, C. and Xu, Z. (2021) DeepSTF: A Deep Spatial-Temporal Forecast Model of Taxi Flow. The Computer Journal, 66, 565-580. [Google Scholar] [CrossRef] 
[5] Wang, Y., Lv, Z., Sheng, Z., Sun, H. and Zhao, A. (2022) A Deep Spatio-Temporal Meta-Learning Model for Urban Traffic Revitalization Index Prediction in the COVID-19 Pandemic. Advanced Engineering Informatics, 53, Article ID: 101678. [Google Scholar] [CrossRef] [PubMed]
[6] Xu, Z., Li, J., Lv, Z., Wang, Y., Fu, L. and Wang, X. (2021) A Graph Spatial-Temporal Model for Predicting Population Density of Key Areas. Computers & Electrical Engineering, 93, Article ID: 107235. [Google Scholar] [CrossRef] [PubMed]
[7] Kumar, S. V. and Vanajakshi, L. (2015) Short-Term Traf-fic Flow Prediction Using Seasonal ARIMA Model with Limited Input Data. European Transport Research Review, 7, 1-9. [Google Scholar] [CrossRef] 
[8] Xu, Z., Lv, Z., Li, J. and Shi, A. (2022) A Novel Approach for Predicting Water Demand with Complex Patterns Based on Ensemble Learning. Water Resources Management, 36, 4293-4312. [Google Scholar] [CrossRef] 
[9] Xu, Z., Li, J., Lv, Z., Dong, C. and Fu, L. (2022) A Classification Method for Urban Functional Regions Based on the Transfer Rate of Empty Cars. IET Intelligent Transport Systems, 16, 133-147. [Google Scholar] [CrossRef] 
[10] Lv, Z., Li, J., Dong, C., Wang, Y., Li, H. and Xu, Z. (2021) DeepPTP: A Deep Pedestrian Trajectory Prediction Model for Traffic Intersection. KSII Transactions on Internet & Information Systems, 15, 2321-2338. [Google Scholar] [CrossRef] 
[11] Li, H., Lv, Z., Li, J., Xu, Z., Yue, W., Sun, H. and Sheng, Z. (2022) Traffic Flow Forecasting in the COVID-19: A Deep Spatial-Temporal Model Based on Discrete Wavelet Transformation. ACM Transactions on Knowledge Discovery from Data, 17, Article No. 64. [Google Scholar] [CrossRef] 
[12] Yuan, G., Li, J., Lv, Z., Li, Y. and Xu, Z. (2021) DDCAttNet: Road Seg-mentation Network for Remote Sensing Images. Wireless Algorithms, Systems, and Applications: 16th International Conference, WASA 2021, Nanjing, 25-27 June 2021, 457-468. [Google Scholar] [CrossRef] 
[13] Lv, Z., Li, J., Xu, Z., Wang, Y. and Li, H. (2021) Parallel Computing of Spatio-Temporal Model Based on Deep Reinforcement Learning. Wireless Algorithms, Systems, and Ap-plications: 16th International Conference, WASA 2021, Nanjing, 25-27 June 2021, 391-403. [Google Scholar] [CrossRef] 
[14] Lv, Z., Li, J., Dong, C. and Zhao, W. (2020) A Deep Spa-tial-Temporal Network for Vehicle Trajectory Prediction. Wireless Algorithms, Systems, and Applications: 15th Interna-tional Conference, WASA 2020, Qingdao, 13-15 September 2020, 359-369. [Google Scholar] [CrossRef] 
[15] Xu, Z., Lv, Z., Li, J., Sun, H. and Sheng, Z. (2022) A Novel Perspective on Travel Demand Prediction Considering Natural Environmental and Socioeconomic Factors. IEEE Intelli-gent Transportation Systems Magazine, 15, 136-159. [Google Scholar] [CrossRef] 
[16] Wang, Y., Zhao, A., Li, J., Lv, Z., Dong, C. and Li, H. (2022) Multi-Attribute Graph Convolution Network for Regional Traffic Flow Prediction. Neural Processing Letters, 1-27. [Google Scholar] [CrossRef] 
[17] Guo, G. and Zhang, T. (2020) A Residual Spatio-Temporal Ar-chitecture for Travel Demand Forecasting. Transportation Research Part C: Emerging Technologies, 115, Article ID: 102639. [Google Scholar] [CrossRef] 
[18] Wei, W. and Yan, X. (2019, November) A Novel Deep Recurrent Neural Network for Short-Term Travel Demand Forecasting under On-Demand Ride Services. IOP Confer-ence Series: Materials Science and Engineering, 688, Article ID: 033022. [Google Scholar] [CrossRef] 
[19] Ye, R., Xu, Z. and Pang, J. (2022) DDFM: A Novel Per-spective on Urban Travel Demand Forecasting Based on the Ensemble Empirical Mode Decomposition and Deep Learn-ing. Proceedings of the 5th International Conference on Big Data Technologies, Qingdao, 23-25 September 2022, 373-379. [Google Scholar] [CrossRef] 
[20] Sun, H., Lv, Z., Li, J., Xu, Z. and Sheng, Z. (2023) Will the Order Be Canceled? Order Cancellation Probability Prediction Based on Deep Residual Model. Transportation Re-search Record. [Google Scholar] [CrossRef] 
[21] Sheng, Z., Lv, Z., Li, J., Xu, Z., Sun, H., Liu, X. and Ye, R. (2023) Taxi Travel Time Prediction Based on Fusion of Traffic Condition Features. Computers and Electrical Engineering, 105, Article ID: 108530. [Google Scholar] [CrossRef] 
[22] Zhang, J., Zheng, Y. and Qi, D. (2017) Deep Spa-tio-Temporal Residual Networks for Citywide Crowd Flows Prediction. Proceedings of the AAAI Conference on Artifi-cial Intelligence, 31, 1655-1661. [Google Scholar] [CrossRef]