We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
ROC Curve Analysis for Classification of Road Defects.
- Authors
Huong Thu Nguyen; Long The Nguyen
- Abstract
ROC analysis is a visual and numerical method used to evaluate the performance of classification algorithms, such as those used to predict the structure and functions from string data. The main objective of the paper is to use the ROC analysis to evaluate the accuracy of the Random Forest algorithm to classify road surface defects on three different sets of data collected from Portugal, Irkutsk city - Russia Federation and Thai Nguyen city - Vietnam. This article summarizes the basics of ROC analysis and interprets the results analysis with other thresholds to build ROC curve. In addition, we present the steps to build a system to automatically classify road surface defects based on visual techniques and machine learning methods.
- Subjects
VIETNAM; IRKUTSK (Russia); PORTUGAL; RECEIVER operating characteristic curves; RANDOM forest algorithms; PAVEMENTS; SURFACE defects; CLASSIFICATION algorithms; MACHINE learning
- Publication
BRAIN: Broad Research in Artificial Intelligence & Neuroscience, 2019, Vol 10, Issue 2, p65
- ISSN
2068-0473
- Publication type
Article