A heterogeneous two-layer graph convolution model for turning traffic prediction with missing data

Jinhua Xu

doi:10.1080/21680566.2025.2497941

A heterogeneous two-layer graph convolution model for turning traffic prediction with missing data

2025-04-30

0

PRE

AI

DOI：10.1080/21680566.2025.2497941

Original

Original request for help

Save

Abstract

En 中文

Turning traffic prediction at urban intersections is very important for the dynamic optimization of traffic management strategies, but accuracy is often influenced by missing data. We propose a novel approach with a Heterogeneous Two-Layer Graph Convolution (HTLGC) model to enhance prediction accuracy while addressing missing data challenges. We construct the urban road network as a heterogeneous two-layer spatial graph, with intersection nodes in the upper layer and turning nodes in the lower layer. To address the missing values, we introduce a feature propagation algorithm. The spatial module equipped with the attention mechanism is used to capture these two distinct levels of spatial information. Moreover, the temporal pattern attention module is applied to more effectively mine features over time. Experiments using license plate recognition data from Xi'an, China, demonstrate that our HTLGC model outperforms baseline algorithms under various missing data rates.

Keywords:

Urban intersection

turning traffic prediction

heterogeneous graph

missing data

attention mechanism

A heterogeneous two-layer graph convolution model for turning traffic prediction with missing data

Abstract

Journal

Organization