A traffic demand forecasting model for internal junction in a multi-level bus terminal with RFID monitoring systems

Chien Hung Wei, Steven I.Jy Chien, Ming Jeng Hsu, De Jun Wang

Research output: Contribution to conferencePaperpeer-review

Abstract

Taipei Bus Station is the first multi-level bus terminal and hub launched in the heart of Taipei metropolitan area. Different from OASIS21 in Nagoya and Port Authority Bus Terminal in New York City, significant congestion has been experienced during peak hours at a T-junction in the terminal due to the three-level structure in the high-density district. Based on the findings of an earlier study by the authors for a signal control model, a traffic demand forecasting model is needed to upgrade the existing pre-timed control strategy to adaptive control level. The artificial neural network approach is employed for constructing the demand forecasting model taking into account the relevant traffic flow information provided by the RFID readers embedded in the terminal monitoring systems. The results show that separate forecasting models for peak and non-peak periods would be desirable for both approaches at the T-junction.

Original languageEnglish (US)
StatePublished - 2013
Event20th Intelligent Transport Systems World Congress, ITS 2013 - Tokyo, Japan
Duration: Oct 14 2013Oct 18 2013

Other

Other20th Intelligent Transport Systems World Congress, ITS 2013
Country/TerritoryJapan
CityTokyo
Period10/14/1310/18/13

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Automotive Engineering
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Transportation
  • Computer Networks and Communications
  • Computer Science Applications

Keywords

  • Adaptive traffic control
  • Artificial neural networks
  • Demand forecasting
  • Multi-level bus terminal
  • RFID

Fingerprint

Dive into the research topics of 'A traffic demand forecasting model for internal junction in a multi-level bus terminal with RFID monitoring systems'. Together they form a unique fingerprint.

Cite this