Improved Sparrow Search Algorithm Optimized Neural Network Analysis of Traffic Congestion

Abstract

Accurate traffic congestion prediction is of great significance for applications such as traffic control and route optimization. However, the traffic situation is affected by many complex factors, and the traditional linear model is difficult to capture the nonlinear interaction information between variables. In recent years, neural networks have been widely used in the analysis and prediction of traffic congestion because of their significant advantages in identifying nonlinear and complex patterns. Firstly, aiming at the shortcomings of sparrow search algorithm, such as easy to fall into local minimum and weak global search ability, a sparrow search algorithm based on Levy flight map** was proposed. The simulation results show that the improved algorithm can effectively overcome the limitations of the original algorithm and improve its performance in terms of convergence accuracy, stability and convergence speed. Secondly, the improved sparrow search algorithm based on Levy flight was used to find the best initial weights and thresholds of the neural network to improve the generalization ability and classification accuracy of the neural network. Finally, the optimized neural network is used to predict the state of traffic congestion. The simulation results show that the improved sparrow search algorithm can improve the performance of the neural network, and can effectively predict the future traffic congestion.