Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs

TL;DR

This paper introduces a novel traffic signal prediction model on transportation networks that combines graph-based heat diffusion kernels with data-driven methods, optimized via Bayesian inference, achieving high accuracy with lower computational costs.

Contribution

It proposes a new hybrid model that merges multiple heat diffusion kernels with data-driven approaches for improved traffic signal forecasting.

Findings

Achieves prediction accuracy comparable to deep neural networks.

Demonstrates effective long-term prediction through periodicity modeling.

Requires less computational effort than state-of-the-art deep learning models.

Abstract

Multivariate time series forecasting poses challenges as the variables are intertwined in time and space, like in the case of traffic signals. Defining signals on graphs relaxes such complexities by representing the evolution of signals over a space using relevant graph kernels such as the heat diffusion kernel. However, this kernel alone does not fully capture the actual dynamics of the data as it only relies on the graph structure. The gap can be filled by combining the graph kernel representation with data-driven models that utilize historical data. This paper proposes a traffic propagation model that merges multiple heat diffusion kernels into a data-driven prediction model to forecast traffic signals. We optimize the model parameters using Bayesian inference to minimize the prediction errors and, consequently, determine the mixing ratio of the two approaches. Such mixing ratio strongly depends on training data size and data anomalies, which typically correspond to the peak hours for traffic data. The proposed model demonstrates prediction accuracy comparable to that of the state-of-the-art deep neural networks with lower computational effort. It notably achieves excellent performance for long-term prediction through the inheritance of periodicity modeling in data-driven models.