Periodic decomposition and feature enhancement fusion for traffic forecasting

Abstract

With the rapid acceleration of urbanization, traffic prediction plays a crucial role in smart city development. This paper proposes an architecture called Periodic Decomposition and Feature Enhancement Fusion (PDGM) aimed at addressing the periodicity issue overlooked in existing traffic prediction methods. PDGM utilizes downsampling techniques to decompose the original traffic data into periodic components and enhances missing data through feature enhancement fusion, thereby improving the accuracy of traffic data prediction. Experimental results of this study demonstrate that PDGM outperforms state-of-the-art baseline models on three benchmark datasets, offering new possibilities for traffic data analysis and prediction tasks.