A Hybrid Learning Framework for Enhancing Bridge Damage Prediction

Bridges are crucial structures for transportation networks, and their structural integrity is paramount. Deterioration and damage to bridges can lead to significant economic losses, traffic disruptions, and, in severe cases, loss of life. Traditional methods of bridge damage detection, often relying...

Full description

Saved in:
Bibliographic Details
Main Authors: Amal Abdulbaqi Maryoosh, Saeid Pashazadeh, Pedram Salehpour
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied System Innovation
Subjects:
Online Access:https://www.mdpi.com/2571-5577/8/3/61
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432791907827712
author Amal Abdulbaqi Maryoosh
Saeid Pashazadeh
Pedram Salehpour
author_facet Amal Abdulbaqi Maryoosh
Saeid Pashazadeh
Pedram Salehpour
author_sort Amal Abdulbaqi Maryoosh
collection DOAJ
description Bridges are crucial structures for transportation networks, and their structural integrity is paramount. Deterioration and damage to bridges can lead to significant economic losses, traffic disruptions, and, in severe cases, loss of life. Traditional methods of bridge damage detection, often relying on visual inspections, can be challenging or impossible in critical areas such as roofing, corners, and heights. Therefore, there is a pressing need for automated and accurate techniques for bridge damage detection. This study aims to propose a novel method for bridge crack detection that leverages a hybrid supervised and unsupervised learning strategy. The proposed approach combines pixel-based feature method local binary pattern (LBP) with the mid-level feature bag of visual words (BoVW) for feature extraction, followed by the Apriori algorithm for dimensionality reduction and optimal feature selection. The selected features are then trained using the MobileNet model. The proposed model demonstrates exceptional performance, achieving accuracy rates ranging from 98.27% to 100%, with error rates between 1.73% and 0% across multiple bridge damage datasets. This study contributes a reliable hybrid learning framework for minimizing error rates in bridge damage detection, showcasing the potential of combining LBP–BoVW features with MobileNet for image-based classification tasks.
format Article
id doaj-art-69d66d25cf56476080f3f5acfe2a5daf
institution Kabale University
issn 2571-5577
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied System Innovation
spelling doaj-art-69d66d25cf56476080f3f5acfe2a5daf2025-08-20T03:27:15ZengMDPI AGApplied System Innovation2571-55772025-04-01836110.3390/asi8030061A Hybrid Learning Framework for Enhancing Bridge Damage PredictionAmal Abdulbaqi Maryoosh0Saeid Pashazadeh1Pedram Salehpour2Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz 51666-16471, IranDepartment of Information Technology, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz 51666-16471, IranDepartment of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz 51666-16471, IranBridges are crucial structures for transportation networks, and their structural integrity is paramount. Deterioration and damage to bridges can lead to significant economic losses, traffic disruptions, and, in severe cases, loss of life. Traditional methods of bridge damage detection, often relying on visual inspections, can be challenging or impossible in critical areas such as roofing, corners, and heights. Therefore, there is a pressing need for automated and accurate techniques for bridge damage detection. This study aims to propose a novel method for bridge crack detection that leverages a hybrid supervised and unsupervised learning strategy. The proposed approach combines pixel-based feature method local binary pattern (LBP) with the mid-level feature bag of visual words (BoVW) for feature extraction, followed by the Apriori algorithm for dimensionality reduction and optimal feature selection. The selected features are then trained using the MobileNet model. The proposed model demonstrates exceptional performance, achieving accuracy rates ranging from 98.27% to 100%, with error rates between 1.73% and 0% across multiple bridge damage datasets. This study contributes a reliable hybrid learning framework for minimizing error rates in bridge damage detection, showcasing the potential of combining LBP–BoVW features with MobileNet for image-based classification tasks.https://www.mdpi.com/2571-5577/8/3/61association rule miningBoVWbridge crackdeep learninglocal binary pattern
spellingShingle Amal Abdulbaqi Maryoosh
Saeid Pashazadeh
Pedram Salehpour
A Hybrid Learning Framework for Enhancing Bridge Damage Prediction
Applied System Innovation
association rule mining
BoVW
bridge crack
deep learning
local binary pattern
title A Hybrid Learning Framework for Enhancing Bridge Damage Prediction
title_full A Hybrid Learning Framework for Enhancing Bridge Damage Prediction
title_fullStr A Hybrid Learning Framework for Enhancing Bridge Damage Prediction
title_full_unstemmed A Hybrid Learning Framework for Enhancing Bridge Damage Prediction
title_short A Hybrid Learning Framework for Enhancing Bridge Damage Prediction
title_sort hybrid learning framework for enhancing bridge damage prediction
topic association rule mining
BoVW
bridge crack
deep learning
local binary pattern
url https://www.mdpi.com/2571-5577/8/3/61
work_keys_str_mv AT amalabdulbaqimaryoosh ahybridlearningframeworkforenhancingbridgedamageprediction
AT saeidpashazadeh ahybridlearningframeworkforenhancingbridgedamageprediction
AT pedramsalehpour ahybridlearningframeworkforenhancingbridgedamageprediction
AT amalabdulbaqimaryoosh hybridlearningframeworkforenhancingbridgedamageprediction
AT saeidpashazadeh hybridlearningframeworkforenhancingbridgedamageprediction
AT pedramsalehpour hybridlearningframeworkforenhancingbridgedamageprediction