Ajou University repository

Efficient Decision Tree-Based Classification Models to Predict Safety Rating for Bridge Maintenance
Citations

SCOPUS

2

Citation Export

DC Field Value Language
dc.contributor.authorHong, Jisu-
dc.contributor.authorJeon, Se Jin-
dc.date.issued2025-03-01-
dc.identifier.issn1943-555X-
dc.identifier.urihttps://aurora.ajou.ac.kr/handle/2018.oak/34568-
dc.identifier.urihttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85208092824&origin=inward-
dc.description.abstractTo address insufficient costs and manpower available for maintenance of aging bridges, recent research has been examining advanced maintenance technologies that can theoretically predict the condition and performance of infrastructure facilities. The current study proposes a method that is intended to predict the safety rating of bridges; among the various machine learning techniques available for this purpose, a decision tree-based classification model has been selected. Using decision tree, random forest, XGBoost (extreme gradient boosting), and LightGBM (light gradient boosting machine), 8,850 bridges on general national roads in Korea were analyzed, and the results were compared. It was possible to identify the variables that have critical impacts on the model during the model formation process. The models were analyzed through various evaluation metrics or indices such as balanced accuracy, recall, ROC (receiver operating characteristic) curve, and AUC (area under the curve). The results showed that the models using random forest, XGBoost, and LightGBM, and not those using a decision tree, exhibited excellent performance in predicting bridge safety ratings. These models achieved a recall of more than 80% for bridges with C and D ratings, which are the main targets of maintenance due to their high degree of aging. Moreover, the AUC exceeded 0.8, indicating that the prediction of bridges with ratings other than C and D was also satisfactory. These results indicate that the multiclass classification model applied in this study, with proper data sampling technique and the optimum parameters, showed improved predictive performance compared with the existing models.-
dc.description.sponsorshipThis work was supported by the Ajou University research fund.-
dc.language.isoeng-
dc.publisherAmerican Society of Civil Engineers (ASCE)-
dc.subject.meshAuthor keyword: machine learning-
dc.subject.meshExtreme gradient boosting (xgboost)-
dc.subject.meshGradient boosting-
dc.subject.meshLight gradient boosting machine-
dc.subject.meshLight gradients-
dc.subject.meshMachine-learning-
dc.subject.meshRandom forests-
dc.subject.meshSafety rating of bridge-
dc.subject.meshSafety ratings-
dc.titleEfficient Decision Tree-Based Classification Models to Predict Safety Rating for Bridge Maintenance-
dc.typeArticle-
dc.citation.number1-
dc.citation.titleJournal of Infrastructure Systems-
dc.citation.volume31-
dc.identifier.bibliographicCitationJournal of Infrastructure Systems, Vol.31 No.1-
dc.identifier.doi10.1061/jitse4.iseng-2524-
dc.identifier.scopusid2-s2.0-85208092824-
dc.identifier.urlhttps://ascelibrary.org/journal/jitse4-
dc.subject.keywordAuthor keywords: Machine learning-
dc.subject.keywordDecision tree-
dc.subject.keywordExtreme gradient boosting (XGBoost)-
dc.subject.keywordLight gradient boosting machine (LightGBM)-
dc.subject.keywordMaintenance-
dc.subject.keywordRandom forest-
dc.subject.keywordSafety rating of bridges-
dc.type.otherArticle-
dc.identifier.pissn1076-0342-
dc.description.isoafalse-
dc.subject.subareaCivil and Structural Engineering-
Show simple item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Jeon, Se Jin Image
Jeon, Se Jin전세진
Department of Civil Systems Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.