How Long a Passenger Waits for a Vacant Taxi -- Large-Scale Taxi Trace Mining for Smart Cities
How Long a Passenger Waits for a Vacant Taxi -- Large-Scale Taxi Trace Mining for Smart Cities
复制标题
DOI：
10.1109/greencom-ithings-cpscom.2013.175
复制
发表时间：
2013-08
期刊：
影响因子：
--
通讯作者：
Guande Qi;Gang Pan;Shijian Li;Zhaohui Wu;Daqing Zhang;Lin Sun;L. Yang
中科院分区：
文献类型：
--
作者：
Guande Qi;Gang Pan;Shijian Li;Zhaohui Wu;Daqing Zhang;Lin Sun;L. Yang
为了实现智能城市，从支持GPS的出租车系统中感知到的真实跟踪数据可以用来使城市交通服务更加智能。例如，乘客知道在一个地点需要多长时间才能找到一辆出租车，这将是非常有帮助的，因为他们可以计划他们的时间表，并选择最好的地点等待。在本文中，我们提出了一种方法来预测等待时间的乘客在给定的时间和地点从历史出租车轨迹。利用出租车到达和离开站点的事件建立了乘客到达模型和出租车空驶模型。利用该模型，可以模拟乘客排队等候的情况，并推断乘客的等待时间。最后，利用大规模真实的出租车GPS轨迹数据集进行实验，验证了该方法的有效性。
To achieve smart cities, real-world trace data sensed from the GPS-enabled taxi system, which conveys underlying dynamics of people movements, could be used to make urban transportation services smarter. As an example, it will be very helpful for passengers to know how long it will take to find a taxi at a spot, since they can plan their schedule and choose the best spot to wait. In this paper, we present a method to predict the waiting time for a passenger at a given time and spot from historical taxi trajectories. The arrival model of passengers and that of vacant taxis are built from the events that taxis arrive at and leave a spot. With the models, we could simulate the passenger waiting queue for a spot and infer the waiting time. The experiment with a large-scale real taxi GPS trace dataset is carried out to verify the proposed method.