ABSTRACT

Predicting traffic states has gained more attention because of its practical significance. However, the existing literature lacks a critical review regarding how to address the spatiotemporal correlation in the ML-based traffic state prediction models from a traffic-oriented perspective. Therefore, this study aims to comprehensively and critically review the spatiotemporal correlation modelling (STCM) approaches adopted for developing ML-based traffic state prediction models and provide future research directions based on traffic-oriented characteristics and ML techniques. Concretely, we investigate the neural network-based traffic state prediction models and characterise the STCM of these models by a proposed systematic review framework including three components: (i) spatial feature representation that demonstrates how the spatial information regarding road network is formulated, (ii) temporal feature representation that illustrates a variety of approaches to extract the temporal features, and (iii) model structure analyses the model layout to address the spatial correlations and temporal correlations simultaneously. Finally, several open challenges regarding incorporating traffic-oriented characteristics such as signal effects with ML techniques are put up with future research directions provided and discussed.

摘要

交通状况预测因其实际意义而受到越来越多的关注。然而，现有文献缺乏关于如何从面向交通的角度解决基于机器学习的交通状态预测模型中的时空相关性的批判性评论。因此，本研究旨在全面、批判性地回顾用于开发基于机器学习的交通状态预测模型所采用的时空相关建模（STCM）方法，并提供基于面向交通的特征和机器学习技术的未来研究方向。具体来说，我们研究了基于神经网络的交通状态预测模型，并通过提出的系统审查框架来表征这些模型的 STCM，该框架包括三个组成部分：（i）空间特征表示，演示如何制定有关道路网络的空间信息，（ii）时间特征表示，说明提取时间特征的各种方法，以及（iii）模型结构分析模型布局以解决空间问题同时相关性和时间相关性。最后，提出了一些关于将面向流量的特征（例如信号效应）与机器学习技术相结合的开放挑战，并提供和讨论了未来的研究方向。