Menu

News

最新消息

2020-02-11
【專題演講】108/12/12 (四)15:30-17:00 洪智傑教授

Abstract

Rapid transit systems are the most important public transportation service modes in many large cities around the world. Understanding route travel time and passengers route choice preference can help transportation authorities to build smart public transportation systems. More and more public transportation systems are now using smart cards to record. The smart card data record the information of the origin and destination of each individual passenger trip and the corresponding travel time. However, routes of passengers inside of the public transportation system are not known. In this talk, I will introduce a series of works to inferring traveling time and route choices preference. By observing the evolution of these works, I will also discuss similarities and differences among these works in terms of network topologies (single line vs. multi-layered graph vs. flatten graph), traveling time models (linear equation vs. Poisson distribution vs. Gaussian distribution), parameter estimation approaches (regression vs. approximation approach vs. standard MLE), and route choice inference.

檔案下載