Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile
This work addresses prediction challenges in transportation systems, but it appears incremental as it builds on existing tensor and statistical models.
The paper tackles the problem of accurately predicting spatiotemporal data, such as passenger flow, by proposing tensor-based methods for long-term and short-term prediction, resulting in improved performance demonstrated in a case study with metro passenger flow data.
Spatiotemporal data is very common in many applications, such as manufacturing systems and transportation systems. It is typically difficult to be accurately predicted given intrinsic complex spatial and temporal correlations. Most of the existing methods based on various statistical models and regularization terms, fail to preserve innate features in data alongside their complex correlations. In this paper, we focus on a tensor-based prediction and propose several practical techniques to improve prediction. For long-term prediction specifically, we propose the "Tensor Decomposition + 2-Dimensional Auto-Regressive Moving Average (2D-ARMA)" model, and an effective way to update prediction real-time; For short-term prediction, we propose to conduct tensor completion based on tensor clustering to avoid oversimplifying and ensure accuracy. A case study based on the metro passenger flow data is conducted to demonstrate the improved performance.