CCNN-former: Combining convolutional neural network and Transformer for image-based traffic time series prediction

Traffic time series prediction is crucial to the development of urban intelligent transportation systems (ITS). Traditional prediction models are mainly designed to extract the spatio-temporal features based on historical traffic flow in the form of time series, ignoring the learning of the implicit periodic patterns hidden in the flow. In addition, most of the models solely employ the historical traffic flow with no more than 12 time steps for prediction. Such short-term input struggles to contain rich, continuous and diverse periodic patterns, limiting their performance. To this end, we propose a model of combining convolutional neural network (CNN) and Transformer (CCNN-Former) tailored for image-based traffic time series prediction. Specifically, we first propose a data conversion module that converts the long-term time series traffic flow into a new representation of image with fixed resolution, ensuring that both short- and long-term information is contained in an image. Then, CNN and Transformer are utilized to learn the image-based features from local and global perspectives, respectively. The core of CCNN-Former is to creatively propose a new long-term time series data imaging strategy and use a computer vision method to extract rich short- and long-term image-based features, achieving the goal of improving prediction performance while maintaining high efficiency. Extensive experiments are conducted on two real-world datasets to demonstrate the superiority of CCNN-Former compared with seven competitive baselines.