Machine learning algorithms for monitoring pavement performance
Saúl Cano-Ortiz, Pablo Pascual-Muñoz, Daniel Castro‐Fresno
Abstract
This work introduces the need to develop competitive, low-cost and applicable technologies to real roads to detect the asphalt condition by means of Machine Learning (ML) algorithms. Specifically, the most recent studies are described according to the data collection methods: images, ground penetrating radar (GPR), laser and optic fiber. The main models that are presented for such state-of-the-art studies are Support Vector Machine, Random Forest, Naïve Bayes, Artificial neural networks or Convolutional Neural Networks. For these analyses, the methodology, type of problem, data source, computational resources, discussion and future research are highlighted. Open data sources, programming frameworks, model comparisons and data collection technologies are illustrated to allow the research community to initiate future investigation. There is indeed research on ML-based pavement evaluation but there is not a widely used applicability by pavement management entities yet, so it is mandatory to work on the refinement of models and data collection methods.