Traffic State Index Prediction Model Based on Hybrid Intelligent Methods

Le résumé fourni par la source

Traffic state index (TSI) is a quantitative indicator to evaluate the degree of traffic congestion. Accurate prediction of the TSI can effectively ease the traffic pressure. This paper presents a prediction model based on the hybrid intelligent method. Firstly, use the cross operator and mutation operator to generate the particles and use the simulated annealing algorithm (SA) to prevent the particles falling into local optimum for the basic particle swarm algorithm (PSO). Secondly, use the improved PSO algorithm to optimize the weights and thresholds of the BP neural network (BPNN). Finally, Train the BPNN to obtain the optimal solution. The hybrid intelligent methods prediction model, named IPSOBP, is verified by using the actual data. The results show that the prediction model has higher accuracy to predict TSI compared with BPNN improved by genetic algorithm (GA) and BPNN improved by PSO.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.