Abstract
In recent years, the convolutional and recurrent neural networks are widely applied in traffic prediction tasks. Traffic speed prediction is an important and challenging topic in intelligent transportation systems. In this case, this paper proposes a hybrid deep learning structure for short-term traffic speed prediction, which combines convolutional neural networks and long short-term memory neural networks together. External factors such as weather condition and air quality can also affect the driving behavior of travelers and cause fluctuation of traffic speed. Based on theories in traffic engineering, we propose a data-fusion method to measure the impact of environmental factors. To enhance the performance of our model, we introduced attention mechanism to our model. With convolutional block attention module, our network could emphasize important channels and pixels of input features and suppress unnecessary ones. Comparing with several deep learning methods and hybrid deep learning structures, an experiment in one region of Suzhou which contains 909 links shows the outperformance of our model. Under different time steps, the prediction error of our model is lower than any other methods in urban expressway, primary-arterial, secondary-arterial, and branch-road. The results indicate that the spatial dependencies, the temporal correlations, and environmental impact should not be ignored in traffic speed prediction tasks.
Highlights
Over the past few years, the rapid progress of urbanization and motorization has caused many urban problems, such as traffic congestion in metropolises around China
We propose a hybrid deep learning framework based on two dimensional convolutional neural networks (CNNs) (2D CNNs) and LSTMs for short-term traffic speed prediction
We introduce convolutional block attention module (CBAM), a widely-used attention block in CNNs to enhance the performance of our model
Summary
Over the past few years, the rapid progress of urbanization and motorization has caused many urban problems, such as traffic congestion in metropolises around China. Deep learning methods achieved great success in computer vision (CV) and natural language process (NLP) Among these various deep learning methods, convolutional neural networks (CNNs) is widely utilized in traffic speed prediction to extract spatial relationships among different road links. With the combination of CNNs, LSTMs and graph neural networks (GCNs), etc., researchers build remarkable spatiotemporal deep learning structures [10], [14] Problems such as complex data preprocessing and restriction of input (e.g., adjacent matrix) cause low portability of these models. We propose a hybrid deep learning framework based on two dimensional CNNs (2D CNNs) and LSTMs for short-term traffic speed prediction. The contributions of our work are two-fold: 1) We design a hybrid deep learning structure HDL-net for short-term traffic speed prediction.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.