arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.06129cs.CVcs.LGstat.ML
收藏

基于图像的城市间交通预测的不确定性量化

Uncertainty Quantification for Image-based Traffic Prediction across Cities

University of Amsterdam(阿姆斯特丹大学);ETH Zurich(苏黎世联邦理工学院);Singapore-ETH Centre(新加坡-苏黎世联邦理工中心)

Alexander Timans, Nina Wiedemann, Nishant Kumar, Ye Hong, Martin Raubal

AI总结:

本文在大规模图像交通数据集上系统比较了多种不确定性量化方法在时间与时空迁移任务中的表现,并利用不确定性估计实现城市交通动态的无监督异常检测,以提升交通预测的可解释性与部署潜力。

摘要:

尽管深度学习模型在交通预测中表现出强大的预测性能,但缺乏可解释性限制了它们在现实世界智能交通系统中的广泛部署。不确定性量化(UQ)方法提供了一种引入概率推理、改进决策并增强模型部署潜力的途径。为了全面了解现有UQ方法在交通预测中的有用性以及所获得的不确定性与城市范围交通动态之间的关系,我们研究了它们在一个跨多个城市和时间段的大规模基于图像的交通数据集上的应用。我们在时间和时空迁移任务上比较了两种认知不确定性和两种偶然不确定性UQ方法,发现可以恢复出有意义的不确定性估计。我们进一步展示了如何利用不确定性估计对城市交通动态变化进行无监督异常检测。我们发现,在莫斯科市的代表性案例研究中,我们的方法能够捕捉交通行为的时间和空间效应。我们的工作朝着在交通预测任务中增强不确定性意识迈出了进一步的一步,旨在强调UQ方法对更好地理解城市交通动态的价值贡献。

英文摘要:

Despite the strong predictive performance of deep learning models for traffic prediction, their widespread deployment in real-world intelligent transportation systems has been restrained by a lack of interpretability. Uncertainty quantification (UQ) methods provide an approach to induce probabilistic reasoning, improve decision-making and enhance model deployment potential. To gain a comprehensive picture of the usefulness of existing UQ methods for traffic prediction and the relation between obtained uncertainties and city-wide traffic dynamics, we investigate their application to a large-scale image-based traffic dataset spanning multiple cities and time periods. We compare two epistemic and two aleatoric UQ methods on both temporal and spatio-temporal transfer tasks, and find that meaningful uncertainty estimates can be recovered. We further demonstrate how uncertainty estimates can be employed for unsupervised outlier detection on changes in city traffic dynamics. We find that our approach can capture both temporal and spatial effects on traffic behaviour in a representative case study for the city of Moscow. Our work presents a further step towards boosting uncertainty awareness in traffic prediction tasks, and aims to highlight the value contribution of UQ methods to a better understanding of city traffic dynamics.

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。

↑