Predictor fusion for short-term traffic forecasting
Predictor fusion for short-term traffic forecasting
复制标题
DOI：
10.1016/j.trc.2018.04.025
复制
发表时间：
2018-07-01
影响因子：
8.3
通讯作者：
Krishnan, Rajesh
中科院分区：
文献类型：
--
作者：
Guo, Fangce;Polak, John W.;Krishnan, Rajesh
短期交通预测可以被定义为在给定历史和当前交通信息的情况下估计短期未来的预期交通状况的过程(Vlahogianni等人，2014)。各种各样的智能运输系统(ITS)应用需要关于运输网络状态各方面的预测性信息。例如，在网络管理应用的情况下，预测性信息使主动(而不是被动)网络和事件策略的发展成为可能(Van Arem等人，1997)。同样，个人旅行者可以使用预测性信息来更有效地计划他们的流动性决策(Dia，2001)。因此，准确的短期交通预测是其应用的关键组成部分之一，近年来一直是广泛研究的主题(Vlahogianni等人，2014)。城市地区的交通状况呈现出随时间的周期性变化(Williams和Hoel，2003)。大多数流量预测方法都利用这种周期性。然而，经常发生的交通情况会受到道路工程、体育赛事和计划外事件和事故等计划内事件的影响，从而偏离了经常发生的模式。可以说，在这种异常情况下，短期预测更为重要，因为交通状况将如何演变到未来存在不确定性。这些因素也大大增加了它的挑战性。
Short-term traffic prediction can be defined as the process of estimating the anticipated traffic conditions in the short-term future given historical and current traffic information (Vlahogianni et al., 2014). A wide variety of Intelligent Transport Systems (ITS) applications require predictive information regarding aspects of the transport network state. For example, in the case of network management applications predictive information enables the development of proactive (rather than reactive) network and incident strategies (Van Arem et al., 1997). Similarly, individual travellers can use the predictive information to plan their mobility decision more efficiently (Dia, 2001). Therefore, accurate short-term traffic prediction is one of the key components in ITS applications, and has been the subject of extensive research in recent years (Vlahogianni et al., 2014).Traffic conditions in urban areas exhibit recurrent patterns over time (Williams and Hoel, 2003). Most traffic prediction methods make use of this periodicity. However, recurrent traffic conditions are affected by planned incidents such as road works, sports events and unplanned incidents and accidents, resulting in a deviation from the recurrent patterns. Short-term prediction is arguably more important during such abnormal conditions because of uncertainty about how the traffic state will evolve into the future. These factors also make it substantially more challenging.