A Hybrid Method for Traffic Flow Forecasting Using Multimodal Deep Learning

• Published in: International journal of computational intelligence systems Vol. 13; no. 1; pp. 85 - 97
• Main Authors: Du, Shengdong, Li, Tianrui, Gong, Xun, Horng, Shi-Jinn
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.01.2020; Springer Nature B.V; Springer
• Subjects: Artificial neural networks; Attention mechanism; Convolutional neural networks; Deep learning; Forecasting; Gated recurrent units; Intelligent transportation systems; Modules; Multimodal deep learning; Research Article; Traffic flow; Traffic flow forecasting; Traffic information; Multimodal deep learning; Attention mechanism; Traffic flow forecasting; Convolutional neural networks; Gated recurrent units
• ISSN: 1875-6891; 1875-6883; 1875-6883
• DOI: 10.2991/ijcis.d.200120.001

Traffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which can jointly and adaptively learn the spatial–temporal correlation features and long temporal interdependence of multi-modality traffic data by an attention auxiliary multimodal deep learning architecture. According to the highly nonlinear characteristics of multi-modality traffic data, the base module of our method consists of one-dimensional convolutional neural networks (1D CNN) and gated recurrent units (GRU) with the attention mechanism. The former is to capture the local trend features and the latter is to capture the long temporal dependencies. Then, we design a hybrid multimodal deep learning framework for fusing share representation features of different modality traffic data by multiple CNN-GRU-Attention modules. The experimental results indicate that the proposed multimodal deep learning model is capable of dealing with complex nonlinear urban traffic flow forecasting with satisfying accuracy and effectiveness.