Understanding private car aggregation effect via spatio-temporal analysis of trajectory data

Zhu Xiao, Hui Fang, Hongbo Jiang, Jing Bai, Hongyang Chen, Licheng Jiao

Abstract: Understanding private car aggregation effect is conducive to a broad range of applications, from intelligent transportation management to urban planning. However, this work is challenging, especially on weekends, due to the inefficient representations of spatio-temporal features for such aggregation effect and the considerable randomness of private car mobility on weekends. In this paper, we propose a deep learning framework for a spatio-temporal attention network (STANet) with a neural algorithm logic unit (NALU), the so-called STANet-NALU, to understand dynamic aggregation effect of private cars on weekends. Specifically, $i)$ we design an improved kernel density estimator (KDE) by defining a log-cosh loss function to calculate the spatial distribution of aggregation effect with guaranteed robustness; $ii)$ we utilize the stay time of private cars as temporal feature to represent the nonlinear temporal correlation of aggregation effect. Next, we propose a spatio-temporal attention module that separately captures the dynamic spatial correlation and nonlinear temporal correlation of private car aggregation effect, and then we design a gate control unit to fuse spatio-temporal features adaptively. Further, we establish the STANet-NALU structure, which provides the model with numerical extrapolation ability to generate promising prediction results of private car aggregation effect on weekends. We conduct extensive experiments based on real-world private car trajectories data. The results reveal that the proposed STANet-NALU outperforms well-known existing methods in terms of various metrics, including the mean absolute error (MAE), root mean square error (RMSE), Kullback-Leibler divergence (KL) and R2.