arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.14304cs.LGeess.SPstat.ML
收藏

基于交通数据的在线学习用于拥堵水平预测的新观点

New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data

TECNALIA, Basque Research and Technology Alliance (BRTA)(TECNALIA,巴斯克研究与技术联盟(BRTA));University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU))

Eric L. Manibardo, Ibai Laña, Jesus L. Lobo, Javier Del Ser

摘要:

这项工作的重点是时间序列数据的分类。当一个时间序列是由非平稳现象产生的,与要预测的类序列相关的模式可能会随着时间的推移而演变(概念漂移)。因此,旨在学习这种模式的预测模型最终可能会变得过时,从而无法维持实际使用的性能水平。为了克服这种模型退化,在线学习方法从随时间到达的新数据样本中增量地学习,并通过实现各种概念漂移策略来适应数据流的最终变化。在这篇手稿中,我们阐述了适合的在线学习方法来预测道路拥堵水平的基础上交通速度时间序列数据。当预测范围增加时,我们得出了关于性能下降的有趣见解。与大多数文献中所做的不同,我们提供了证据,证明在设计和调整学习模型之前,评估类的分布随时间的重要性。以上的练习可能会提示在目标下不同拥堵水平的可预测性。实验结果进行了讨论,在实际的交通速度数据的感应线圈部署在西雅图(美国)。分析了几种在线学习方法,从传统的增量式学习算法到更详细的深度学习模型。如报告的结果所示,当增加预测范围时,由于类沿时间的分布,所有模型的性能都严重下降,这支持了我们关于在设计模型之前分析这种分布的重要性的主张。

英文摘要:

This work focuses on classification over time series data. When a time series is generated by non-stationary phenomena, the pattern relating the series with the class to be predicted may evolve over time (concept drift). Consequently, predictive models aimed to learn this pattern may become eventually obsolete, hence failing to sustain performance levels of practical use. To overcome this model degradation, online learning methods incrementally learn from new data samples arriving over time, and accommodate eventual changes along the data stream by implementing assorted concept drift strategies. In this manuscript we elaborate on the suitability of online learning methods to predict the road congestion level based on traffic speed time series data. We draw interesting insights on the performance degradation when the forecasting horizon is increased. As opposed to what is done in most literature, we provide evidence of the importance of assessing the distribution of classes over time before designing and tuning the learning model. This previous exercise may give a hint of the predictability of the different congestion levels under target. Experimental results are discussed over real traffic speed data captured by inductive loops deployed over Seattle (USA). Several online learning methods are analyzed, from traditional incremental learning algorithms to more elaborated deep learning models. As shown by the reported results, when increasing the prediction horizon, the performance of all models degrade severely due to the distribution of classes along time, which supports our claim about the importance of analyzing this distribution prior to the design of the model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑