Graph Markov Network for Traffic Forecasting with Missing Data (2019-12-10T00:00:00.000000Z)

TL;DR

This study considers the traffic network as a graph and defines the transition between network-wide traffic states at consecutive time steps as aGraph Markov process, which proposes a new neural network architecture for spatial-temporal data forecasting, i.e. the graph Markov network (GMN) and a spectral graph MarkOV network (SGMN).

Authors

Zhiyong Cui

1 papers

Longfei Lin

1 papers

Ziyuan Pu

1 papers

Yinhai Wang

1 papers

TL;DR

Authors

References48 items

Missing Data in Traffic Estimation: A Variational Autoencoder Imputation Method

On Attribution of Recurrent Neural Network Predictions via Additive Decomposition

A Bayesian tensor decomposition approach for spatiotemporal traffic data imputation

Forecasting Transportation Network Speed Using Deep Capsule Networks With Nested LSTM Models

LSTM-based traffic flow prediction with missing data

GAIN: Missing Data Imputation using Generative Adversarial Nets

On the imputation of missing data for road traffic forecasting: New insights and novel techniques

Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting

A Deep Generative Adversarial Architecture for Network-Wide Spatial-Temporal Traffic-State Estimation

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

An efficient realization of deep learning for traffic data imputation

A clustering-based approach for data-driven imputation of missing traffic data

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Recurrent Neural Networks for Multivariate Time Series with Missing Values

Tensor based missing traffic data completion with spatial–temporal correlation

Short-Term Traffic Prediction Based on Dynamic Tensor Completion

A Comparative Study of Three Multivariate Short-Term Freeway Traffic Flow Forecasting Methods With Missing Data

Orthogonal Eigenvector Matrix of the Laplacian

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

A hybrid approach to integrate fuzzy C-means based imputation method with genetic algorithm for missing traffic volume data estimation

Adam: A Method for Stochastic Optimization

Traffic prediction, data compression, abnormal data detection and missing data imputation: An integrated study based on the decomposition of traffic time series

Big data and its technical challenges

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Short-term traffic forecasting: Where we are and where we’re going

Multivariate Short-Term Traffic Flow Forecasting Using Time-Series Analysis

A bayesian network approach to traffic flow forecasting

Gaussian Markov Random Fields: Theory and Applications

Travel-time prediction with support vector regression

Comparison of parametric and nonparametric models for traffic flow forecasting

Long Short-Term Memory

Dynamic prediction of traffic volume through Kalman Filtering

Cell-Speed Prediction Neural Network (CPNN): A Deep Learning Approach for Trip-Based Speed Prediction

Spatial-temporal traffic speed patterns discovery and incomplete data recovery via SVD-combined tensor decomposition

Deep Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction

Traffic Prediction

The quality of loop data and the health of California ’ s freeway loop detectors

Multivariate Vehicular Traffic Flow Prediction: Evaluation of ARIMAX Modeling

On the contributions of this study

Application of Subset Autoregressive Integrated Moving Average Model for Short-Term Freeway Traffic Volume Forecasting

We propose a new neural network structure, i.e. the graph Markov network, based on the proposed graph Markov process for dealing with missing values and forecasting traﬃc state simultaneously

We consider the traﬃc network as a graph and deﬁne the transition between network-wide traﬃc states at consecutive time steps as a graph Markov process

By incorporating the spectral graph convolution operation, we also propose a spectral graph Markov network

Experiment results tested on three real-world network-wide traﬃc state datasets show that the proposed models can achieve superior prediction performance in terms of both accuracy and eﬃciency

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names