Traffic flow prediction is regarded as an important concept used in traffic planning, traffic design, and traffic management. In this study, the authors propose a multi-component attention (MCA) method for traffic flow prediction, which may jointly and adaptively understand components of long-term trends, seasons, and traffic flow residuals that result from multi-dimensional decomposition. According to the highly non-linear nature of traffic flow, the proposed module consists of a one-dimensional convolutional neural network, a bidirectional long short-term memory, and a bidirectional mechanism with an attention mechanism. The former captures local trend characteristics of residuals, while the latter captures trends and seasonal time adjustments. Due to the randomness, irregularity, and periodicity of traffic flow at intersections, target flow prediction is related to various sequences. Through the introduction of the attention mechanism, highly related historical information may be connected for multi-component flow data in the final prediction. Compared to seasonal autoregressive integral moving average model, artificial neural network, and recurrent neural network, the experimental results demonstrated that the proposed MCA model can meet the accuracy and effectiveness of complex non-linear urban traffic flow prediction models.
Urban traffic flow online prediction based on multi-component attention mechanism
IET Intelligent Transport Systems ; 14 , 10 ; 1249-1258
2020-08-03
10 pages
Article (Journal)
Electronic Resource
English
convolutional neural nets , multidimensional decomposition , multicomponent flow data , MCA model , multicomponent attention method , traffic management , one-dimensional convolutional neural network , traffic design , nonlinear urban traffic flow prediction models , urban traffic flow online prediction , multicomponent attention mechanism , traffic flow residuals , recurrent neural network , traffic planning , autoregressive moving average processes , target flow prediction , time series , road traffic , bidirectional mechanism , long-term trends , recurrent neural nets
Metadata by IET is licensed under CC BY 3.0
Urban traffic flow online prediction based on multi‐component attention mechanism
Wiley | 2020
|Traffic flow prediction method based on multi-head attention mechanism
European Patent Office | 2023
|Multi-node traffic flow prediction method based on simplified attention mechanism
European Patent Office | 2025
|Traffic flow prediction method based on attention mechanism
European Patent Office | 2022
|Traffic flow prediction method based on space-time attention mechanism
European Patent Office | 2024
|