Multi-task and multi-view learning based on particle swarm optimization for short-term traffic forecasting

Abstract

Spatiotemporal prediction modeling of traffic is an important issue in the field of spatiotemporal data mining. However, it is encountering multiple challenges such as the global spatiotemporal correlation between predictive tasks, balanced between spatiotemporal heterogeneity and the global predictive power of the model, and parameter optimization of prediction models. Most existing short-term traffic prediction methods only emphasize spatiotemporal dependence and heterogeneity, so it is difficult to get satisfactory prediction accuracy. In this paper, spatiotemporal multi-task and multi-view feature learning models based on particle swarm optimization are combined to concurrently address these challenges. First, cross-correlation is used to construct the spatiotemporal proximity view, periodic view and trend view of each road segment to characterize spatiotemporal dependence and heterogeneity. Second, the prediction results of three spatiotemporal views are obtained using a set of kernels, which is further regarded as a high-level heterogeneous semantic feature as the input of the multi-task multi-view feature learning model. Third, additional regularization terms (e.g., group Lasso penalty, graph Laplacian regularization) are utilized to constrain all tasks to select a set of shared features and ensure the relatedness between tasks and consistency between views, so that the predictive model has a good global predictive ability and can capture global spatiotemporal correlation in the road network. Finally, particle swarm optimization is introduced to obtain the optimal parameter set and enhance the training speed of the proposed model. Experimental studies on real vehicular-speed datasets collected on city roads demonstrate that the proposed model significantly outperform the existing nine baseline methods in terms of prediction accuracy. The results suggest that the proposed model merits further attention for other spatiotemporal prediction tasks, such as water quality, crowd flow, owing to the versatility of the modeling process for spatiotemporal data.