Traffic Flow Prediction with Missing Data Imputed by Tensor Completion Methods

Missing data is inevitable and ubiquitous in intelligent transportation systems (ITSs). A handful of completion methods have been proposed, among which the tensor-based models have been shown to be the most advantageous for missing traffic data imputation. Despite their superior imputation accuracies, the adoption of these imputed data is not uniform in modern ITSs applications. The primary goal of this paper is to explore how to use tensor completion methods to support ITSs. In particular, we study how to improve traffic flow prediction accuracy under different missing scenarios. Specifically, three common missing scenarios including element-wise random missing, time-structured missing, and space-structured missing are considered. Four classical tensor completion models including Smooth PARAFAC Decomposition based Completion (SPC), CP Decomposition-based (CP-WOPT) Completion, Tucker Decomposition-based Completion (TDI), and High-accuracy Low-rank Tensor Completion (HaLRTC) are used to impute the missing data. Four well-known prediction methods including Support Vector Regression (SVR), K-nearest Neighbor (KNN), Gradient Boost Regression Tree (GBRT), and Long Short-term Memory (LSTM) are tested. The simple mean value interpolation completed traffic data is regarded as the baseline data. The extensive experiments show that improvements of traffic flow prediction can be achieved by increasing missing traffic data imputation accuracy at most cases. Interestingly we find that prediction accuracy cannot be improved by an imputation model when the sparsely observed training datasets already provide sufficient training samples.