A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery

TL;DR

This paper presents a novel spatio-temporal traffic data recovery method using latent feature analysis, effectively capturing underlying patterns to improve the accuracy of missing data estimation in intelligent transportation systems.

Contribution

It introduces a matrix completion approach based on hidden feature analysis that leverages spatio-temporal correlations for improved traffic data recovery.

Findings

The model achieves lower evaluation criterion values, indicating better performance.

It accurately estimates continuous missing traffic data.

The approach effectively captures spatio-temporal patterns for data recovery.

Abstract

Missing data is an inevitable and common problem in data-driven intelligent transportation systems (ITS). In the past decade, scholars have done many research on the recovery of missing traffic data, however how to make full use of spatio-temporal traffic patterns to improve the recovery performance is still an open problem. Aiming at the spatio-temporal characteristics of traffic speed data, this paper regards the recovery of missing data as a matrix completion problem, and proposes a spatio-temporal traffic data completion method based on hidden feature analysis, which discovers spatio-temporal patterns and underlying structures from incomplete data to complete the recovery task. Therefore, we introduce spatial and temporal correlation to capture the main underlying features of each dimension. Finally, these latent features are applied to recovery traffic data through latent feature analysis. The experimental and evaluation results show that the evaluation criterion value of the model is small, which indicates that the model has better performance. The results show that the model can accurately estimate the continuous missing data.