Representation of Traffic Congestion Data for Urban Road Traffic Networks Based on Pooling Operations

Abstract

In order to improve the efficiency of transportation networks, it is critical to forecast traffic congestion. Large-scale traffic congestion data have become available and accessible, yet they need to be properly represented in order to avoid overfitting, reduce the requirements of computational resources, and be utilized effectively by various methodologies and models. Inspired by pooling operations in deep learning, we propose a representation framework for traffic congestion data in urban road traffic networks. This framework consists of grid-based partition of urban road traffic networks and a pooling operation to reduce multiple values into an aggregated one. We also propose using a pooling operation to calculate the maximum value in each grid (MAV). Raw snapshots of traffic congestion maps are transformed and represented as a series of matrices which are used as inputs to a spatiotemporal congestion prediction network (STCN) to evaluate the effectiveness of representation when predicting traffic congestion. STCN combines convolutional neural networks (CNNs) and long short-term memory neural network (LSTMs) for their spatiotemporal capability. CNNs can extract spatial features and dependencies of traffic congestion between roads, and LSTMs can learn their temporal evolution patterns and correlations. An empirical experiment on an urban road traffic network shows that when incorporated into our proposed representation framework, MAV outperforms other pooling operations in the effectiveness of the representation of traffic congestion data for traffic congestion prediction, and that the framework is cost-efficient in terms of computational resources.

Efficient and Safe Strategies for Intersection Management: A Review

“…Compared with the traditional shortest path algorithm which considers the static network as the core, the first part of this guiding method considers the potential traffic jam, gives the optimal driving suggestion for different times of day, designs the equilibrium Markov chain model, and this method is used to dispatch vehicles to alleviate urban congestion. Inspired by the pooling operation in deep learning, a representation framework [ 33 ] for traffic congestion data in urban road traffic network is proposed. The framework consists of a grid-based urban road traffic network partitioning and a pooling operation that reduces multiple values to aggregate values.…”

Reliable and Rapid Traffic Congestion Detection Approach Based on Deep Residual Learning and Motion Trajectories

“…For a large dataset of low-frame-rate videos gathered from a traffic surveillance system, they achieved an accuracy of 95.77%. Zhang et al [21] proposed a congestion prediction model using CNNs and a long short-term memory neural network. Raw snapshots of traffic congestion maps were represented as a series of matrices to train their model.…”

Detecting Traffic Incidents Using Persistence Diagrams

“…Detecting incidents in traffic data can be formulated as an anomaly detection problem. Approaches in this formulation include: dynamic clustering [13] or Support Vector Machines [14] to detect anomalous trajectories, autoencoders to learn regularity of video sequences [15], motion reconstruction [16], and convolutional neural networks to predict congestion in traffic networks [17]. In this paper, we also view incident detection as an anomaly detection problem, with our approach using TDA to identify outliers.…”