LR-BCA: Label Ranking for Bridge Condition Assessment

Bridge condition assessment (BCA) plays an important role in modern bridge management. Existing methods are time-consuming, labor-intensive and error-prone. The use of machine learning for BCA can effectively solve the above problems. However, large amount label noise dataset severely affected performance model. In this paper, we present effective ranking approach (LR-BCA). Our proposed LR-BCA method considers natural order relationship between ratings. Moreover, a heuristic data cleaning (HDC) is dataset. HDC firstly identifies all conflict examples, then iteratively filters out noise. Experimental results on real-world confirm effectiveness demonstrate that our achieves 99% Top-2 accuracy, which highly competitive compared to baseline methods.