ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-temporal Graph Attention and Bidirectional Recurrent United Neural Networks

TL;DR

This paper introduces ST-GIN, a deep learning model that combines graph attention and bidirectional recurrent networks to accurately impute missing traffic data by capturing spatial and temporal correlations.

Contribution

The paper presents a novel deep learning framework integrating graph attention and bidirectional RNNs specifically for traffic data imputation, outperforming existing methods.

Findings

Outperforms benchmark imputation techniques

Effectively captures spatial and temporal correlations

Demonstrates high accuracy in traffic data recovery

Abstract

Traffic data serves as a fundamental component in both research and applications within intelligent transportation systems. However, real-world transportation data, collected from loop detectors or similar sources, often contains missing values (MVs), which can adversely impact associated applications and research. Instead of discarding this incomplete data, researchers have sought to recover these missing values through numerical statistics, tensor decomposition, and deep learning techniques. In this paper, we propose an innovative deep learning approach for imputing missing data. A graph attention architecture is employed to capture the spatial correlations present in traffic data, while a bidirectional neural network is utilized to learn temporal information. Experimental results indicate that our proposed method outperforms all other benchmark techniques, thus demonstrating its effectiveness.