A Deep Learning Framework About Traffic Flow Forecasting for Urban Traffic Emission Monitoring System.

Baozhen Yao,Yansheng Yao,Mingheng Zhang,Rui Feng,Xiaopeng Shen,Ankun Ma

doi:10.3389/fpubh.2021.804298

Abstract

As urban traffic pollution continues to increase, there is an urgent need to build traffic emission monitoring and forecasting system for the urban traffic construction. The traffic emission monitoring and forecasting system's core is the prediction of traffic emission's evolution. And the traffic flow prediction on the urban road network contributes greatly to the prediction of traffic emission's evolution. Due to the complex non-Euclidean topological structure of traffic networks and dynamic heterogeneous spatial-temporal correlations of traffic conditions, it is difficult to obtain satisfactory prediction results with less computation cost. To figure these issues out, a novel deep learning traffic flow forecasting framework is proposed in this paper, termed as Ensemble Attention based Graph Time Convolutional Networks (EAGTCN). More specifically, each component of our model contains two major blocks: (1) the global spatial patterns are captured by the spatial blocks which are fused by the Graph Convolution Network (GCN) and spatial ensemble attention layer; (2) the temporal patterns are captured by the temporal blocks which are composed by the Time Convolution Net (TCN) and temporal ensemble attention layers. Experiments on two real-world datasets demonstrate that our model obtains more accurate prediction results than the state-of-the-art baselines at less computation expense especially in the long-term prediction situation.

Highlights

With the rapid development of urban traffic construction, traffic emission has attracted more and more attention from public
The main contributions of this paper are summarized as follows: [1] We propose an ensemble attention mechanism which is able to dig out the global dynamic heterogeneous spatialtemporal correlations from traffic sequence
Qi,j′ = softmax Qi,j where X:,c : c+1,: ∈ Rn×1×L denotes one feature slice from the spatial ensemble attention module’s input X:,;,: ∈ Rn×3×L, where n is the number of nodes, three is the number of input graph signal’s features, and L is the length of the time length

Summary

INTRODUCTION

With the rapid development of urban traffic construction, traffic emission has attracted more and more attention from public. Attention Based Spatial Temporal Graph Convolutional Networks (ASTGCN) [12] presented by Guo et al confused STGCN with attention layers which were used to capture the dynamic spatial correlations among nodes relying only on traffic flow data These GCN based methods still have many problems. A novel deep learning model named Ensemble Attention Graph Time Convolutional Networks (EAGTCN) is proposed to predict traffic flow in the road network dimension. This model can capture more comprehensive dynamic heterogeneous spatialtemporal features of traffic data effectively and efficiently.

METHODOLOGY

EXPERIMENTS

DATA AVAILABILITY STATEMENT