Spatio-temporal forecasting of traffic flow data represents a typical problem
in the field of machine learning, impacting urban traffic management systems.
Traditional statistical and machine learning methods cannot adequately handle
both the temporal and spatial dependencies in these complex traffic flow
datasets. A prevalent approach in the field is to combine graph convolutional
networks and multi-head attention mechanisms for spatio-temporal processing.
This paper proposes a wavelet-based temporal attention model, namely a
wavelet-based dynamic spatio-temporal aware graph neural network (W-DSTAGNN),
for tackling the traffic forecasting problem. Benchmark experiments using
several statistical metrics confirm that our proposal efficiently captures
spatio-temporal correlations and outperforms ten state-of-the-art models on
three different real-world traffic datasets. Our proposed ensemble data-driven
method can handle dynamic temporal and spatial dependencies and make long-term
forecasts in an efficient manner.

本文提出了一种基于小波的动态时空感知图神经网络 (W-DSTAGNN)，用于解决交通流量预测问题，实验证实该方法有效地捕捉时空相关性，在三个不同的真实交通数据集上胜过了十种最先进的模型，可以以高效的方式处理动态时空依赖性并进行长期预测。

基于小波的时间关注提升交通预测

Wavelet-based Temporal Attention Improves Traffic Forecasting

Developing accurate models for traffic trajectory predictions is crucial for
achieving fully autonomous driving. Various deep neural network models have
been employed to address this challenge, but their black-box nature hinders
transparency and debugging capabilities in a deployed system. Glass-box models
offer a solution by providing full interpretability through methods like
\ac{GAM}. In this study, we evaluate an efficient additive model called
\ac{EBM} for traffic prediction on three popular mixed traffic datasets:
\ac{SDD}, \ac{InD}, and Argoverse. Our results show that the \ac{EBM} models
perform competitively in predicting pedestrian destinations within \ac{SDD} and
\ac{InD} while providing modest predictions for vehicle-dominant Argoverse
dataset. Additionally, our transparent trained models allow us to analyse
feature importance and interactions, as well as provide qualitative examples of
predictions explanation. The full training code will be made public upon
publication.

通过评估一种高效的可加性模型，本研究在三个热门混合交通数据集上对交通预测进行了评估，结果显示该模型在预测行人目的地方面表现竞争力，对以车辆为主的数据集则提供较为适度的预测，而透明的训练模型使我们能够分析特征的重要性和相互作用，并提供预测解释的质量性示例。