论文部分内容阅读
A new machine learning method called the evolving fuzzy participatory learning model(ePL)is employed to predict the freeway travel time online.The ePL model has a promising nonlinear mapping ability,which is well suitable for traffic prediction.The generalized recursive least square(GRLS)is used to improve the estimation accuracy of the models inner parameters for the first time.This model is also a fuzzy control model.Its output is the forecasting result which is also the fuzzy reasoning result.Utilizing the freeway data from the PeMS(the Caltrans Performance Measurement System),the authors test this model by comparing it to other travel time prediction approaches.The performances show that this model has a good adaptability and a high prediction accuracy.This model can be used to predict the travel time in practical applications.