Traffic Guidance Oriented Model of Traffic State Probability Forecast

Abstract In order to obtain the accurate and objective traffic state information to meet the demand of traffic guidance, and in view of the stochastic property and complexity of the traffic flow evolution on the urban road and the uncertainty of traffic state discrimination, an algorithm of Logistic regression for traffic state probability forecast is put forward based on the analysis of the mapping relationships between traffic state and traffic flow parameters. The proposed algorithm explores the function relationships of traffic state and the influencing factors by means of Logistic regression and thus gives the probability prediction of the traffic state of the next time period. Finally, according to the proposed algorithm, the grading traffic state probability forecast tests of different time periods is carried out using the field traffic flow data. The results of independent sample test indicate that the model has a finer precision and stability.