A MULTI STREAM FUTURE FUSION APPROACH FOR TRAFFIC PREDICTION

Abstract

Accurate and timely traffic flow prediction is crucial for intelligent transportation systems (ITS). Recent advances in graphbased neural networks have achievedpromising prediction results. However, some challenges remain, especially regarding graph construction and the time complexity of models. In this paper, we propose a multistream feature fusion approach to extract and integrate rich features from traffic data and leverage a data-driven adjacent matrix instead of the distance-basedmatrix to construct graphs. We calculate the Spearman rank correlation coefficient between monitor stations to obtain the initial adjacent matrix and fine-tune it while training. As to the model, we construct a multi-stream feature fusion block (MFFB) module, which includes a three-channel network and the soft attention mechanism. The three-channel networks are graph convolutional neural network (GCN), gated recurrent unit (GRU) and fully connected neural network (FNN), which are used toextract spatial, temporal and other features, respectively. The softattention mechanism is utilized to integrate the obtained features. The MFFB modules are stacked, and a fully connected layer and a convolutional layer are used to make predictions.We conduct experiments on two real-world traffic prediction tasks and verify that our proposed approach outperforms the state-of-the-art methods within an acceptable time complexity.