Classification of Road Surface Quality Based on SVM Method
Adhelinia Afenika, Putu Harry Gunawan, Dede Tarwidi · Journal of Physics Conference Series · 2020
Abstract Damaged and potholes roads can occur due to rain puddles, too many heavy vehicles, poor asphalt quality, or maybe long road life. Damaged roads can hamper activities and endanger the safety of road users. It is necessary to monitor road quality periodically which is conducted by government, so that roads improvement can be done quick as possible. The aim of this study is to build a system that can classify roads surface quality. Support Vector Machine (SVM) classifications method is used to classify roads based on roadworthiness. In this study, 300 road surface data which contains good/smooth and damage quality of road are used. The simulation results show that SVM model can classify road surface data into two classes with average accuracy of 93%. The results can be a recommendation for government to prioritize which roads need to be improved.