The implementation of Markov bias corrected grey system in freeway travel time prediction

摘要

The purpose of this study is to develop a freeway travel time prediction model and, combined with real-time database, to obtain the most precise travel time prediction. First, a grey system theory for travel time prediction is developed, and then Markov Bias Correction mechanism is used for bias correction. Prediction is divided into "day-of-week" in time category because of that, travel time is corresponding to travel pattern and travel pattern itself is highly related to whether it is weekday or weekend. In the link section, this study divided the path into pairs of interchanges because of the information obtained. And then, construct a real-time database, and connect to Taiwan Area National Freeway Bureau via internet for real-time travel speed, and uses this information on freeway travel time prediction. Besides prediction, this study also uses this information for calibration.