Traffic Signal Prediction on Transportation Networks Using Spatio-Temporal Correlations on Graphs

  title={Traffic Signal Prediction on Transportation Networks Using Spatio-Temporal Correlations on Graphs},
  author={Semin Kwak and Nikolas Geroliminis and Pascal Frossard},
  journal={IEEE Transactions on Signal and Information Processing over Networks},
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… 

Figures and Tables from this paper

TwoResNet: Two-level resolution neural network for traffic forecasting on freeway networks

A forecasting model called two-level resolutions deep neural network (TwoResNet) that achieves competitive prediction accuracy compared to state-of-the-art methods, especially showing excellent performance for long-term predictions.

Joint Time-Vertex Fractional Fourier Transform

It is theoretically show that the proposed JFRT generalizes the JFT and satisfies the properties of index additivity, reversibility, reduction to identity, and unitarity (for certain graph topologies).

Few-Shot Traffic Prediction with Graph Networks using Locale as Relational Inductive Biases

A graph network (G N )-based deep learning model L OCALE G N is developed that depicts the traffic dynamics using localized data aggregating and updating functions, as well as the node-wise recurrent neural networks.



Travel Time Prediction for Congested Freeways With a Dynamic Linear Model

This work designs a dynamic linear models (DLM) with model parameters defined at each time unit to describe the spatio-temporal characteristics of time-series traffic data and suggests an optimal linear predictor in the minimum mean square error (MMSE) sense.

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

This paper proposes a general graph neural network framework designed specifically for multivariate time series data that outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.

Spatial-Temporal Graph Attention Networks: A Deep Learning Approach for Traffic Forecasting

A novel deep learning framework, Spatial-Temporal Graph Attention Networks (ST-GAT), a graph attention mechanism is adopted to extract the spatial dependencies among road segments and a LSTM network is introduced to extract temporal domain features.

DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

A dual self-attention network (DSANet) for highly efficient multivariate time series forecasting, especially for dynamic-period or nonperiodic series, which is effective and outperforms baselines.

Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting

In this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model, which indicates significant improvement of prediction accuracy, robust and generalization of the model.

An End-to-End Adaptive Input Selection With Dynamic Weights for Forecasting Multivariate Time Series

An end-to-end recurrent neural network framework equipped with an adaptive input selection mechanism to improve the prediction performance for multivariate time series forecasting and gives a beneficial advantage to interpret variable importance.

Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning

This work proposed a deep-meta-learning based model, entitled ST-MetaNet, to collectively predict traffic in all location at once, consisting of a recurrent neural network to encode the traffic, a meta graph attention network to capture diverse spatial correlations, and a meta recurrent Neural network to consider diverse temporal correlations.

Graph WaveNet for Deep Spatial-Temporal Graph Modeling

This paper proposes a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling by developing a novel adaptive dependency matrix and learn it through node embedding, which can precisely capture the hidden spatial dependency in the data.