A hybrid deep learning based traffic flow prediction method and its understanding. (May 2018)

• Record Type: Journal Article
• Authors: Wu, Yuankai; Tan, Huachun; Qin, Lingqiao; Ran, Bin; Jiang, Zhuxi
• Is Part Of: Transportation research. Volume 90(2018)
• Page Start: 166
• Page End: 180
• Publication Date: 2018-05
• Subjects: Traffic flow prediction -- Recurrent neural network -- Convolutional neural network -- Attention model -- Deep neural network visualization; Transportation -- Periodicals; Transportation -- Technological innovations -- Periodicals; 388.011
• DOI: 10.1016/j.trc.2018.03.001
• Languages: English
• ISSNs: 0968-090X

Abstract

Highlights: This paper addresses the multi-step ahead prediction tasks. Develop a deep learning-based approach to fully mine spatial-temporal features of traffic flow. Employ visualization approach to understand the work mechanism of neural networks on traffic flow data. Abstract: Deep neural networks (DNNs) have recently demonstrated the capability to predict traffic flow with big data. While existing DNN models can provide better performance than shallow models, it is still an open issue of making full use of spatial-temporal characteristics of the traffic flow to improve their performance. In addition, our understanding of them on traffic data remains limited. This paper proposes a DNN based traffic flow prediction model (DNN-BTF) to improve the prediction accuracy. The DNN-BTF model makes full use of weekly/daily periodicity and spatial-temporal characteristics of traffic flow. Inspired by recent work in machine learning, an attention based model was introduced that automatically learns to determine the importance of past traffic flow. The convolutional neural network was also used to mine the spatial features and the recurrent neural network to mine the temporal features of traffic flow. We also showed through visualization how DNN-BTF model understands traffic flow data and presents a challenge to conventional thinking about neural networks in the transportation field that neural networks is purely a "black-box" model. Data from open-access database PeMS was used to validate the proposed DNN-BTF model on a long-term horizon prediction task. Experimental results demonstrated that our method outperforms the state-of-the-art approaches.