Restricted Research - Award List, Note/Discussion Page
Fiscal Year: 2023
388 Sam Houston State University (142276)
Principal Investigator: Mousa, Momen R.
Total Amount of Contract, Award, or Gift (Annual before 2011): $ 37,500
Exceeds $250,000 (Is it flagged?): No
Start and End Dates: 1/15/23 - 1/14/25
Restricted Research: YES
Academic Discipline: Engineering Techology
Department, Center, School, or Institute: Deparment of Enginerring Technology
Title of Contract, Award, or Gift: Machine Learning-Based Tool to Predict the Retroreflectivity of Pavement Markings in the U.S.
Name of Granting or Contracting Agency/Entity:
National Academy of Sciences
Program Title: n/a
Note:
SAMs 1.1.1: The project will begin with a meeting with an expert advisory panel consisting of three to five experts with experience in traffic control devices and traffic safety. At least two members will come from State DOTs. Additional members may be added from academia or industry. There will be an IDEA advisor assigned by the IDEA program who would participate in all panel meetings and receive all reports. The research team will use the National Transportation Product Evaluation Program (NTPEP) data mine to collect retroreflectivity data along with the corresponding key variables for at least 5,000 pavement marking lines. The research team will use about 90% of the data collected in Task 2 to train six different powerful supervised machine-learning models to predict the retroreflectivity at different time intervals (1, 2, 3, 11, 12, 15, 21, 24, 27, 33, and 36 months) based on the initial retroreflectivity and the corresponding variables. The remaining 10% of the collected data will be used in the final testing of the developed machine-learning models. The testing results of the six different machine-learning models will be compared, and the model yielding optimum accuracy will be selected.
Discussion: No discussion notes