Dynamic Graph Representation Learning for Passenger Behavior Prediction
Beihang University(北京航空航天大学);School of Transportation Science and Engineering, Beihang University(北京航空航天大学交通科学与工程学院);Zhongguancun Lab(中关村实验室);Hosei University(法政大学);Faculty of Computer and Information Science, Hosei University(法政大学计算机与信息科学学院)
Mingxuan Xie, Tao Zou, Junchen Ye, Bowen Du, Runhe Huang
Passenger behavior prediction aims to track passenger travel patterns through historical boarding and alighting data, enabling the analysis of urban station passenger flow and timely risk management. This is crucial for smart city development and public transportation planning. Existing research primarily relies on statistical methods and sequential models to learn from individual historical interactions, which ignores the correlations between passengers and stations. To address these issues, this paper proposes DyGPP, which leverages dynamic graphs to capture the intricate evolution of passenger behavior. First, we formalize passengers and stations as heterogeneous vertices in a dynamic graph, with connections between vertices representing interactions between passengers and stations. Then, we sample the historical interaction sequences for passengers and stations separately. We capture the temporal patterns from individual sequences and correlate the temporal behavior between the two sequences. Finally, we use an MLP-based encoder to learn the temporal patterns in the interactions and generate real-time representations of passengers and stations. Experiments on real-world datasets confirmed that DyGPP outperformed current models in the behavior prediction task, demonstrating the superiority of our model.
Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph
Beihang University(北京航空航天大学);The University of Queensland(昆士兰大学);Didichuxing(滴滴出行);University of Leeds(利兹大学)
近年来,乘车服务越来越普遍,因为它们为乘客提供了巨大的便利。作为一个基本问题,及时预测不同地区的乘客需求对于有效的交通流控制和路线规划至关重要。由于空间和时间模式都是不可或缺的乘客需求预测,相关研究已经从纯时间序列发展到用于建模历史乘客需求数据的图结构数据,其中通过经由不同关系边(例如,起点-目的地关系、地理距离等)。因此,时空乘客需求记录自然地在构造的图中携带动态模式,其中边还编码关于方向和体积的重要信息(即,两个连接区域之间的乘客需求的权重)。然而,现有的基于图的解决方案未能同时考虑动态、有向和加权(DDW)图的这三个关键方面,导致在学习用于乘客需求预测的图表示时表现力有限。因此,我们提出了一种新的时空图注意力网络,即Gallat(Graph prediction with all attention)作为解决方案。在Gallat中,通过全面结合DDW图的这三个内在属性,我们构建了三个注意力层,以充分捕获所有历史时隙中不同区域之间的时空依赖关系。此外,该模型采用一个子任务进行预训练,使其能够更快地获得准确的结果。我们在真实世界的数据集上评估了所提出的模型,我们的实验结果表明,Gallat优于最先进的方法。
Predicting Subway Passenger Flows under Incident Situation with Causality
Key Laboratory of Road and Traffic Engineering, Ministry of Education at Tongji University(同济大学交通工程教育重点实验室);Urban Mobility Institute, Tongji University(同济大学城市交通研究院)
A Deep Spatio-Temporal Fuzzy Neural Network for Passenger Demand Prediction
New Jersey Institute of Technology(新泽西理工学院);NEC Laboratories America, Inc.(美国NEC实验室公司);Texas Southern University(德克萨斯南方大学);University of Houston(休斯顿大学)
CSP-AIT-Net: A contrastive learning-enhanced spatiotemporal graph attention framework for short-term metro OD flow prediction with asynchronous inflow tracking
Study on Key Technologies of Transit Passengers Travel Pattern Mining and Applications based on Multiple Sources of Data
在本研究中,我们提出了一系列的方法来挖掘公交乘客的出行模式和行为偏好,然后我们使用这些知识来调整和优化公交系统。贡献包括:1)为了提高数据的有效性:a)提出了一种新的AFC(Automated Fare Collection)系统和AVL(Automated Vehicle Location)系统之间数据的时间差异校正方法,该方法将数据事件转换为信号,并应用时域相关技术检测和校正它们之间的相对差异。b)通过结合历史数据和乘客售票时间戳,我们引入和补偿AVL数据集中的缺失信息。2)为了推断乘客的下车点,我们引入了一个最大概率模型,结合乘客的家乡,以恢复其完整的过境轨迹从半完整的登机记录,然后我们提出了一个增强的活动识别算法,能够指定乘客的短期活动,从普通的换乘。最后,分析了公交客流的时空特征。3)发现旅客出行需求。我们整合每个乘客在多天的轨迹数据,构建一个混合出行图(HTG)。然后,我们使用深度搜索算法来获得空间封闭的过境出行链;最后,我们使用封闭的过境出行链的乘客,从不同的角度来研究他们的出行模式。最后,通过对乘客关键出行链的聚合,对城市公交走廊进行分析。4)推导出8个影响因素,构建了不同情景下乘客出行选择模型。接下来,我们验证我们的模型使用乘客重新分配模拟。最后,我们对乘客的时间选择偏好进行了综合分析,并利用这些信息来优化城市交通系统。
Exploring the impact of weather on Metro demand forecasting using machine learning method
Qiushi Honors College, Tianjin University(天津大学求是学部);School of Traffic and Transportation, Beijing Jiaotong University(北京交通大学交通运输学院);Maynooth International Engineering College, Fuzhou University(福州大学梅努斯国际工程学院);Harbin Institute of Technology(哈尔滨工业大学);Beijing Forestry University(北京林业大学)
A Mobile Data-Driven Hierarchical Deep Reinforcement Learning Approach for Real-time Demand-Responsive Railway Rescheduling and Station Overcrowding Mitigation
Chang'an University(长安大学);University of Leeds(利兹大学)