Dynamic traffic demand uncertainty prediction using radio-frequency identification data and link volume data

摘要: Dynamic traffic demand is crucial for developing effective strategies and algorithms real-time management control. The uncertainty of provides additional information while its prediction very complicated inadequately investigated in the existing literature. Recently, radio-frequency identification (RFID) technology has been deployed to monitor condition traffic. In this study, authors propose a modelling system predict dynamic using RFID data link volume. includes an optimisation model calculate historical terms origin–destination matrix, state-space solved by Kalman filter demand, GARCH capture conditional variance predicted demand. Performance measures are applied evaluate accuracy. case study Nanjing, China shows that desirable performance successfully uncertainties