This note explores the idea of utilising a state-space model, congruent with the underlying equations of the Kalman filter with control input, for reconstructing the state of crowdedness in a transit network. The envisaged role of the proposed scheme is twofold: first, to provide an estimate of the state of crowdedness given input data on vehicle movement, on passenger inflow/outflow at stations and on measured crowdedness; second, to trigger localised requests for feedback based on the estimated system state as well as on the data assimilation performance indices. The latter is applicable to a scenario where the crowdedness is measured through passenger feedback. The feedback loop is conceptualised to be realised with a participatory crowd-sensing smartphone-based system in which reported perceived levels of crowdedness are assimilated in near-real-time with the aim of improving the estimation of the model state. Presented model is also applicable for assimilating other relevant measurements, for instance, vehicle weighing, automatic passenger counting, aggregated smartcard data or passive wireless device monitoring data.
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。
Joint Optimization of Pattern, Headway, and Fleet Size of Multiple Urban Transit Lines with Perceived Headway Consideration and Passenger Flow Allocation
Northwestern University（西北大学）；Argonne National Laboratory（阿贡国家实验室）
Bulk Service Queueing for Transit Resilience under Short Random Service Suspensions
Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；New York University（纽约大学）；University of California, Berkeley（加州大学伯克利分校）；Northeastern University（东北大学）；Massachusetts Institute of Technology（麻省理工学院）
Strategizing Equitable Transit Evacuations: A Data-Driven Reinforcement Learning Approach
School of Sustainable Engineering and the Built Environment, Arizona State University（亚利桑那州立大学可持续工程与建筑环境学院）；University of California, Berkeley（加州大学伯克利分校）
