Forecasting Multiple-Period Freeway Link Travel Times Using Modular Neural Networks

An examination is conducted on how realtime information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods

Dongjoo Park; Laurence R. Rilett

2007

Scholarcy highlights

  • An examination is conducted on how realtime information gathered as part of intelligent transportation systems can be used to predict link travel times for one through five time periods
  • The historical link travel times are classified based on an unsupervised clustering technique
  • Actual link travel times from Houston, Texas, collected as part of the automatic vehicle identification system of the Houston Transtar system were used as a test bed
  • It was found that the modular artificial neural network outperformed a conventional singular ANN
  • The results of the best modular ANN were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results
  • The results of the best modular artificial neural network were compared with existing link travel time techniques, including a Kalman filtering model, an exponential smoothing model, a historical profile, and a real-time profile, and it was found that the modular ANN gave the best overall results

Need more features? Save interactive summary cards to your Scholarcy Library.