Full Program »
Using Machine Learning for Road Maintenance Cost Estimates in Brazil: a case study in the Federal District
This paper presents the application of Machine Learning algorithms, such as artificial neural network and k-means as an alternative for estimating the services required for the highway conservation services in Brazil, based on data related to the highways of the Federal District. A database was created containing data on routine maintenance history, road catalogue of road solutions and price lists. Next, the algorithms were applied and evaluated. It was found that the K-means algorithm was better suited to the problem.