Learning traffic as videos: Short-term traffic flow prediction using mixed-pointwise convolution and channel attention mechanism

In the construction of intelligent transportation systems, short-term traffic flow prediction is of great significance for the advancement of traffic network management. But due to the presence of many complex factors in both spatial and temporal domains, it remains a complex and challenging task. Existing literature usually employs the convolutional neural network (CNN)-based methods in capturing spatiotemporal correlations. These CNN-based methods often use a single-channel data structure to represent different periodic patterns, which makes the model susceptible to over-parameterization when capturing periodic dependencies and prone to information loss after convolution. To overcome these limitations, this paper presents a hybrid deep learning method for short -term traffic flow prediction. In this method, a video-shaped multi-channel data structure is designed to repre-sent different periodic patterns more efficiently. Next, a new mixed-pointwise convolution is introduced for capturing periodic dependencies without the negative impacts mentioned above. Lastly, an improved channel attention mechanism is proposed to learn channel inter-dependencies with controllable parameter usage. The proposed method is lightweight, yet highly effective. Compared to the state-of-the-art baseline method, it reduces the root mean squared error by up to 6.7% on the PeMSD4 dataset and 13.3% on the PeMSD7 dataset, while also achieving substantial improvement in two additional metrics, exhibiting strong robustness and great scalability across various settings.

Automated summary

Short-term traffic flow prediction is of great significance for intelligent transportation systems and traffic network management. Existing methods often use convolutional neural networks to capture spatiotemporal correlations, but face challenges due to complex factors. This paper proposes a hybrid deep learning method that improves prediction accuracy by designing a video-shaped multi-channel data structure and introducing a new mixed-pointwise convolution method.