Traffic Data Imputation

Traffic data imputation aims to reconstruct missing values in traffic datasets, crucial for reliable analysis and application in intelligent transportation systems. Current research heavily focuses on leveraging spatiotemporal correlations within the data using advanced techniques like tensor decomposition, graph neural networks, and recurrent neural networks, often incorporating semantic information about the road network. These improved imputation methods enhance the accuracy and efficiency of downstream applications, such as traffic prediction and optimization, by providing more complete and reliable data for analysis. The development of robust and scalable imputation techniques is vital for maximizing the utility of increasingly large and complex traffic datasets.

Papers

October 20, 2024

FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation
Shaokang Cheng, Nada Osman, Shiru Qu, Lamberto Ballan
Conditional Diffusion Model Traffic Data Traffic Datasets Temporal Traffic Traffic Data Imputation

May 11, 2023

Spatiotemporal Regularized Tucker Decomposition Approach for Traffic Data Imputation
Wenwu Gong, Zhejun Huang, Lili Yang
Traffic Network Tucker Decomposition Temporal Regularization Traffic Data Imputation

May 10, 2023

ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-temporal Graph Attention and Bidirectional Recurrent United Neural Networks
Zepu Wang, Dingyi Zhuang, Yankai Li, Jinhua Zhao, Peng Sun, Shenhao Wang, Yulin Hu
Neural Network Deep Learning Uncertainty Quantification Graph Attention Traffic Data Bidirectional Recurrent Neural Network Traffic Data Imputation

April 18, 2023

A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies
Li Jiang, Ting Zhang, Qiruyi Zuo, Chenyu Tian, George P. Chan, Wai Kin, Chan
Time Series Temporal Dependency Deep Learning Framework Spatio tempOral Spatiotemporal Imputation Traffic Data Imputation

January 27, 2023

Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding
Kunpeng Zhang, Lan Wu, Liang Zheng, Na Xie, Zhengbing He
Traffic Data Spatiotemporal Network Traffic Data Imputation

December 3, 2022

Laplacian Convolutional Representation for Traffic Time Series Imputation
Xinyu Chen, Zhanhong Cheng, HanQin Cai, Nicolas Saunier, Lijun Sun
Urban Traffic Velocity Field Laplacian Representation Traffic Data Imputation

August 16, 2022

A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery
Yuting Ding, Di Wu
Traffic Data Latent Feature Temporal Traffic Traffic Data Imputation

May 19, 2022

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns
Tong Nie, Guoyang Qin, Jian Sun
Constructive Approach Complex Pattern Missing Value Tensor Based Spatiotemporal Traffic Tensor Rank Low Rank Tensor Completion Schatten $P$ Norm Traffic Data Imputation

Traffic Data Imputation

Papers

FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation

Spatiotemporal Regularized Tucker Decomposition Approach for Traffic Data Imputation

ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-temporal Graph Attention and Bidirectional Recurrent United Neural Networks

A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies

Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding

Laplacian Convolutional Representation for Traffic Time Series Imputation

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

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns