Traffic flow prediction based on optimized hidden Markov model

Abstract

In order to alleviate the current urban traffic congestion pressure and provide accurate and reliable traffic condition information, it is difficult to select the optimal state parameters for the original Hidden Markov model (HMM) and the state number redundancy determined during the training process leads to the model over-provisioning. The problem of weak is integration and generalization. An improved Hidden Markov Model for traffic flow prediction is proposed to more effectively fit the actual urban road intersection traffic flow. In the calculation of the negative log-likelihood function, an Akaike information criterion (AIC) or a Bayesian information criterion (BIC) penalty term is added, and the Baum-Welch algorithm is combined to optimize the optimal state number of the model. Experiments are carried out based on the collected real traffic flow and GPS feature data. The results show that the optimized hidden Markov model is superior to the original model in the accuracy and generalization ability of traffic flow prediction.