期刊
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
卷 129, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.trc.2021.103226
关键词
Spatiotemporal traffic data; High-dimensional data; Missing data imputation; Low-rank tensor completion; Linear unitary transformation; Quadratic variation
资金
- Natural Sciences and Engineering Research Council (NSERC) of Canada
- Fonds de recherche du Quebec - Nature et technologies (FRQNT)
- Canada Foundation for Innovation (CFI)
- Institute for Data Valorisation (IVADO)
This paper focuses on addressing the missing data imputation problem for large-scale spatiotemporal traffic data by developing a scalable tensor learning model called LSTC-Tubal, which effectively preserves the complex correlations in the data with lower computational cost.
Missing value problem in spatiotemporal traffic data has long been a challenging topic, in particular for large-scale and high-dimensional data with complex missing mechanisms and diverse degrees of missingness. Recent studies based on tensor nuclear norm have demonstrated the superiority of tensor learning in imputation tasks by effectively characterizing the complex correlations/dependencies in spatiotemporal data. However, despite the promising results, these approaches do not scale well to large data tensors. In this paper, we focus on addressing the missing data imputation problem for large-scale spatiotemporal traffic data. To achieve both high accuracy and efficiency, we develop a scalable tensor learning model-Low-Tubal-Rank Smoothing Tensor Completion (LSTC-Tubal)-based on the existing framework of Low-Rank Tensor Completion, which is well-suited for spatiotemporal traffic data that is characterized by multidimensional structure of location x time of day x day. In particular, the proposed LSTC-Tubal model involves a scalable tensor nuclear norm minimization scheme by integrating linear unitary transformation. Therefore, tensor nuclear norm minimization can be solved by singular value thresholding on the transformed matrix of each day while the day-to-day correlation can be effectively preserved by the unitary transform matrix. Before setting up the experiment, we consider some real-world data sets, including two large-scale 5-min traffic speed data sets collected by the California PeMS system with 11160 sensors: 1) PeMS-4W covers the data over 4 weeks (i.e., 288 x 28 time points), and 2) PeMS-8W covers the data over 8 weeks (i.e., 288 x 56 time points). We compare LSTC-Tubal with some state-of-the-art baseline models, and find that LSTC-Tubal can achieve competitively accuracy with a significantly lower computational cost. In addition, the LSTC-Tubal will also benefit other tasks in modeling large-scale spatiotemporal traffic data, such as network-level traffic forecasting.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据