Dynamic Travel Time Prediction with Real-Time and Historic Data

Abstract

Travel time prediction has been an interesting research area for decades during which various prediction models have been developed. This paper discusses the results and accuracy generated by different prediction models developed in this study. The employed real-time and historic data are provided by the Transportation Operations Coordinating Committee, which collected them using road side terminals (RST) installed on the New York State Thruway. All the tagged vehicles equipped with EZ pass are scanned by RSTs, while dynamic information (e.g., vehicle entry times and associated RST numbers) are recorded. The emphasis of this study is focused on modeling real-time and historic data for travel time prediction. Factors that would affect the prediction results are explored. The Kalman filtering algorithm is applied for travel time prediction because of its significance in continuously updating the state variable as new observations. Results reveal that during peak hours, the historic path-based data used for travel-time prediction are better than link-based data due to smaller travel-time variance and larger sample size.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 296 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.