Predicting intersection queue with neural network models

Predicting intersection queue with neural network models

0.00 Avg rating0 Votes
Article ID: iaor1996232
Country: United States
Volume: 3C
Issue: 3
Start Page Number: 175
End Page Number: 191
Publication Date: Jun 1995
Journal: Transportation Research. Part C, Emerging Technologies
Authors: ,
Keywords: queues: applications, neural networks
Abstract:

To capture the complex nature of intersection queue dynamics, this study has explored the use of neural network models with data from extensive simulation experiments. The proposed models, although lacking in mathematical elegance, are capable of providing the acceptable prediction accuracy (more than 90%) at 3 time-steps ahead. As each time-step is as short as 3s, the resulting information on queue evolution is sufficiently detailed for both responsive signal control and intersection operations. To accommodate the differences in available surveillance systems, this study has also investigated the most suitable neural network structure for each proposed queue model with extensive exploratory analyses.

Reviews

Required fields are marked *. Your email address will not be published.