|
|
Project Details
AbstractPublic transportation plays a vital role in providing mobility and accessibility in small urban and rural areas. In order to maintain an efficient public transportation system, the small urban and rural transit systems need to keep their existing transit revenue vehicles in proper conditions. But these transit systems are struggling to maintain a state of good repair for their revenue vehicles. Most of them do not have any effective ways to manage their revenue vehicles and do not have a good analytical tool for investment decision. In order to predict the service life of revenue vehicles, the SURCOM research team developed a state of good repair machine learning predictive model for small urban and rural transit systems. The team also developed a financial analytical tool to estimate the current backlog and predict yearly projected vehicle replacement cost. Even though these tools are very useful for decision-makers, they are not available for them to use. These tools are developed on local machine and only the research team can generate state of good repair reports for any small urban and rural transit agencies. Therefore, the objective of this project is to develop a user-friendly web application for transit professionals in order to produce state of good repair reports from the predicted results of machine learning model on small urban and rural transit system's rolling stocks. These tools can be very useful for transit managers to prioritize investment needs for rehabilitation and replacement of small urban and rural urban transit agencies. The state DOTs and the FTA will also be able to see the overall condition of the rolling stocks in any state's small urban and rural transit systems. |
