Traffic flow prediction method based on bidirectional linear recurrent neural network

Abstract

In order to improve the rationality and effectiveness of intelligent traffic control and management on urban roads, a bidirectional linear recurrent neural network-based traffic flow prediction method is proposed from the perspective of spatial and temporal characteristics of traffic flow. The method effectively combines the characteristics of fast and accurate bilinear polynomial solution and dynamic calibration of recurrent neural network, and adopts particle swarm algorithm to realize the dynamic pruning process of redundant neurons and weights, which improves the convergence speed and prediction accuracy of the algorithm. The algorithm is trained and experimented with video data, and a comparative analysis is conducted. The results show that the method can achieve accurate prediction of road traffic flow, the traffic flow prediction accuracy reaches more than 90%, meeting the data accuracy requirements of actual traffic management and control, and the convergence speed of the algorithm has also been significantly improved.

Research on traffic flow prediction method based on deep learning

“…In domestic research, Zhang [1] et al proposed the application of the EEMD+BiGRU combination model in short-term traffic flow prediction. The input data was decomposed using the signal decomposition EEMD method, and then a short-term and short-term memory neural network was used; Tian [2] et al proposed a short-term traffic flow prediction method based on the combination of CEEMDAN-SE and LSSA-GRU, which extracts features from input data in multi vector space; Wang [3] et al proposed a traffic flow prediction model based on a multi time scale spatiotemporal graph network, which combines the spatiotemporal graph network with a convolutional neural network to predict the flow data of traffic nodes; Meng [4] et al used a dynamic spatiotemporal neural network to predict urban traffic flow.…”