Application Research on Machine Learning and Statistical Forecasting Algorithm in Traffic Information Forecasting System

摘要

This paper proposes an algorithm model based on the machine learning and statistic forecasting method to forecast the traffic information. It constructs the forecasting specimens set by the mechanism learning of the machine learning, forecasts the short time traffic information by the data fit return technology, and constructs the knowledge base, which uses the concept of knowledge maturation degree to judge the application probability rate of the forecasted information in the traffic information forecasting system. It implements the short time traffic flowing forecasting in the traffic information forecasting system by this algorithm model, and it gets the effective to forecast the change of the traffic flowing state on some routes or transport corridor in the few minutes of the future.