Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis
For managers of road infrastructure, culvert deterioration is a major concern since culvert failures can cause serious risks to the traveling public. The efficiency of the cost- and labor-intensive culvert inspection and maintenance process can be improved by properly identifying the key impact fact...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2024-01-01
|
Series: | Advances in Civil Engineering |
Online Access: | http://dx.doi.org/10.1155/2024/9574203 |
_version_ | 1797301893577310208 |
---|---|
author | Ce Gao Zhibin Li Hazem Elzarka Hongyan Yan Peijin Li |
author_facet | Ce Gao Zhibin Li Hazem Elzarka Hongyan Yan Peijin Li |
author_sort | Ce Gao |
collection | DOAJ |
description | For managers of road infrastructure, culvert deterioration is a major concern since culvert failures can cause serious risks to the traveling public. The efficiency of the cost- and labor-intensive culvert inspection and maintenance process can be improved by properly identifying the key impact factors on culvert condition deterioration. Although the use of machine learning (ML) techniques to predict culvert conditions has been proven to be a promising tool for enhancing culvert management and enabling proactive scheduling of maintenance tasks, the information provided by the developed ML models has been given little attention for further use and analysis. By utilizing the predictor importance results of an evaluated decision tree (DT) culvert condition prediction model and the Mann–Whitney U test, this study provided insights to the identification of the key variables influencing culvert deterioration. According to the findings, five impact factors, including culvert span, pH, age, rise, and cover height, often have significant impact on the condition ratings of culverts made of various materials. In addition, such a statistical test-assisted factor identification process offered a way of identifying and enhancing the input variable selection for predictive ML model development. |
first_indexed | 2024-03-07T23:29:04Z |
format | Article |
id | doaj.art-d62101df56bb46b8a5c2dff86396cabe |
institution | Directory Open Access Journal |
issn | 1687-8094 |
language | English |
last_indexed | 2024-03-07T23:29:04Z |
publishDate | 2024-01-01 |
publisher | Hindawi Limited |
record_format | Article |
series | Advances in Civil Engineering |
spelling | doaj.art-d62101df56bb46b8a5c2dff86396cabe2024-02-21T00:00:19ZengHindawi LimitedAdvances in Civil Engineering1687-80942024-01-01202410.1155/2024/9574203Machine Learning and Statistical Test–Based Culvert Condition Impact Factor AnalysisCe Gao0Zhibin Li1Hazem Elzarka2Hongyan Yan3Peijin Li4School of Civil EngineeringSchool of Civil Engineering and ArchitectureCollege of Engineering and Applied ScienceSchool of Construction ManagementSchool of Construction ManagementFor managers of road infrastructure, culvert deterioration is a major concern since culvert failures can cause serious risks to the traveling public. The efficiency of the cost- and labor-intensive culvert inspection and maintenance process can be improved by properly identifying the key impact factors on culvert condition deterioration. Although the use of machine learning (ML) techniques to predict culvert conditions has been proven to be a promising tool for enhancing culvert management and enabling proactive scheduling of maintenance tasks, the information provided by the developed ML models has been given little attention for further use and analysis. By utilizing the predictor importance results of an evaluated decision tree (DT) culvert condition prediction model and the Mann–Whitney U test, this study provided insights to the identification of the key variables influencing culvert deterioration. According to the findings, five impact factors, including culvert span, pH, age, rise, and cover height, often have significant impact on the condition ratings of culverts made of various materials. In addition, such a statistical test-assisted factor identification process offered a way of identifying and enhancing the input variable selection for predictive ML model development.http://dx.doi.org/10.1155/2024/9574203 |
spellingShingle | Ce Gao Zhibin Li Hazem Elzarka Hongyan Yan Peijin Li Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis Advances in Civil Engineering |
title | Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis |
title_full | Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis |
title_fullStr | Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis |
title_full_unstemmed | Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis |
title_short | Machine Learning and Statistical Test–Based Culvert Condition Impact Factor Analysis |
title_sort | machine learning and statistical test based culvert condition impact factor analysis |
url | http://dx.doi.org/10.1155/2024/9574203 |
work_keys_str_mv | AT cegao machinelearningandstatisticaltestbasedculvertconditionimpactfactoranalysis AT zhibinli machinelearningandstatisticaltestbasedculvertconditionimpactfactoranalysis AT hazemelzarka machinelearningandstatisticaltestbasedculvertconditionimpactfactoranalysis AT hongyanyan machinelearningandstatisticaltestbasedculvertconditionimpactfactoranalysis AT peijinli machinelearningandstatisticaltestbasedculvertconditionimpactfactoranalysis |