Multivariate long-time series traffic passenger flow prediction using causal convolutional sparse self-attention MTS-Informer

• Published in: Neural computing & applications Vol. 35; no. 34; pp. 24207 - 24223
• Main Authors: Liu, Miaonan, Wang, Wei, Hu, Xianhui, Fu, Yunlai, Xu, Fujin, Miao, Xinying
• Format: Journal Article
• Language: English
• Published: London Springer London 01.12.2023; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural networks; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Deep learning; Flow distribution; Flow stability; Forecasting; Image Processing and Computer Vision; Intelligent transportation systems; Machine learning; Methods; Neural networks; Operation scheduling; Original Article; Passengers; Prediction models; Probability and Statistics in Computer Science; R&D; Research & development; Standard error; Time series; Traffic flow; Traffic models; Transportation planning; Trends; Urban rail; Wavelet transforms; Stationarity detection; Causal convolutional networks; Traffic passenger flow prediction; Informer
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-023-09003-z

As an important part of the operation preparation process of the intelligent transportation system, the passenger flow distribution law and forecast can guide the urban rail transit to formulate a reasonable operation scheduling plan. Due to the complexity, multi-variables, and instability of traffic passenger flow data, accurate passenger flow prediction takes a lot of work. Based on a convolutional neural network, a causal convolution self-attention traffic passenger flow prediction model MTS-Informer framework is proposed. This method follows the changing law of auxiliary variables, adopts the stabilization method to reduce the instability of the original sequence, and uses the causal convolution feature to improve the ability of the model’s self-attention mechanism to extract local information from the input sequence. The weakening effect of the self-attention mechanism ensures that it can learn similarly to the differential features in the original sequence data. In addition, the stationarity detection of the original sequence data is added. The experimental results show that the fitting degree of the sample data is significantly improved, and the standard error decreases between 10 and 40%, which verifies the effectiveness of the proposed modeling technique. It has higher prediction accuracy and operating efficiency and can provide a basis for urban traffic passenger flow prediction.