| Autor: |
Didier M. Valdés-Díaz, Bryan Ruiz-Cruz, Johnathan Ruiz-González, Benjamin Colucci-Rios, Wandaliz Torres-García |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
Advances in Intelligent Systems and Computing ISBN: 9783319938844 |
| DOI: |
10.1007/978-3-319-93885-1_85 |
| Popis: |
The Puerto Rico Dynamic Toll Lane (DTL) is a reversible managed lane facility located in the median of a segment of freeway PR-22. Safety and operational concerns have emerged with vehicles traveling with higher speed profiles than the posted speed limit. The objective of this paper is focused on the application of a Random Forest Model to perform a safety and operational analysis based on driving simulator data of the virtual environment of PR-22 DTL using the University of Puerto Rico at Mayaguez (UPRM) of the simulation. This model ranks the importance of independent variables for each performance measure (i.e. operating speed and acceleration noise). Research results indicate that the most important variable for the performance measure operating speed is the posted speed limit, resulting with the highest increase in variation of the mean square error (MSE). |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
