Missing data imputation for traffic congestion data based on joint matrix factorization

作者：

Highlights：

• Propose a matrix factorization-based model to impute the missing traffic values.

• Consider periodicity, road similarity and temporal coherence in the imputation model.

• Outperform the baselines in the task of traffic congestion value imputation.

摘要

•Propose a matrix factorization-based model to impute the missing traffic values.•Consider periodicity, road similarity and temporal coherence in the imputation model.•Outperform the baselines in the task of traffic congestion value imputation.

论文关键词：Traffic data imputation,Joint matrix factorization,Traffic congestion patterns

论文评审过程：Received 24 January 2021, Revised 25 March 2021, Accepted 30 April 2021, Available online 5 May 2021, Version of Record 7 May 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107114