Hybrid Transfer Learning and Support Vector Machine Models for Asphalt Pavement Distress Classification

被引:0
|
作者
Apeagyei, Alex [1 ]
Ademolake, Toyosi Elijah [1 ]
Anochie-Boateng, Joseph [2 ]
机构
[1] Univ East London, Sch Architecture Comp & Engn, London, England
[2] Univ Pretoria, Fac Engn Built Environm & Informat Technol, Pretoria, South Africa
关键词
deep learning; support vector machines; infrastructure management and system preservation; transfer learning; maintenance data modeling; asphalt pavement distresses; pavement condition evaluation;
D O I
10.1177/03611981241239958
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Pavement condition evaluation plays a crucial role in assisting with the management of the highway infrastructure. However, the current methods used for assessing pavement conditions are costly, time-consuming, and subjective. There is a growing need to automate these assessment tactics and leverage low-cost technologies to enable widespread deployment. This study aims to develop robust and highly accurate models for classifying asphalt pavement distresses using transfer learning (TL) techniques based on pretrained deep learning (DL) networks. This topic has gained considerable attention in the field since 2015 when DL became the mainstream choice for various computer vision tasks. While progress has been made in TL model development, challenges persist in areas of accuracy, repeatability, and training cost. To tackle these challenges, this study proposes hybrid models that combine DL networks with support vector machines (SVMs). Three strategies were evaluated: single DL models using transfer learning (TLDL), hybrid models combining DL and SVM (DL+SVM), and hybrid models combining TLDL and SVM (TLDL+SVM). The performance of each strategy was assessed using statistical metrics based on the confusion matrix. Results consistently showed that the TLDL+SVM strategy outperformed the other approaches in accuracy and F1 scores, regardless of the DL network type. On average, the hybrid models achieved an accuracy of 95%, surpassing the 80% accuracy of the best single model and the 55% accuracy for DL+SVM without TL. The results clearly indicate that employing transfer-learned models as feature extractors, in combination with SVM as the classifier, consistently achieves exceptional performance.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] A novel approach for asphalt pavement invisible distress classification prediction by machine learning algorithms
    Shi, Jicun
    Jia, Shili
    Bai, Chengxiang
    Wang, Duanyi
    [J]. INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING, 2024, 25 (01)
  • [2] Evaluation on Performance of Asphalt Pavement Based on Support Vector Machine
    Zhao, Jing
    Wang, Xuancang
    Fan, Zhenyang
    Wang, Peicheng
    [J]. Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science), 2020, 48 (09): : 116 - 123
  • [3] RETRACTED: Pavement Performance Evaluation of Asphalt Expressway Based on Machine Learning Support Vector Machine (Retracted Article)
    Sun, Qiao
    Wang, Guan
    Sui, Yanpeng
    Zakaria, Ideris
    [J]. WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2022, 2022
  • [4] A Hybrid Model for Prediction in Asphalt Pavement Performance Based on Support Vector Machine and Grey Relation Analysis
    Wang, Xuancang
    Zhao, Jing
    Li, Qiqi
    Fang, Naren
    Wang, Peicheng
    Ding, Longting
    Li, Shanqiang
    [J]. JOURNAL OF ADVANCED TRANSPORTATION, 2020, 2020
  • [5] Proximal Support Vector Machine Based Pavement Image Classification
    Na, Wei
    Tao, Wang
    [J]. 2012 IEEE FIFTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI), 2012, : 686 - 688
  • [6] Evaluation of deep learning models for classification of asphalt pavement distresses
    Apeagyei, Alex
    Ademolake, Toyosi Elijah
    Adom-Asamoah, Mark
    [J]. INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING, 2023, 24 (01)
  • [7] Quantum machine learning for support vector machine classification
    Kavitha, S. S.
    Kaulgud, Narasimha
    [J]. EVOLUTIONARY INTELLIGENCE, 2024, 17 (02) : 819 - 828
  • [8] Quantum machine learning for support vector machine classification
    S. S. Kavitha
    Narasimha Kaulgud
    [J]. Evolutionary Intelligence, 2024, 17 : 819 - 828
  • [9] A Transfer Learning Architecture Based on a Support Vector Machine for Histopathology Image Classification
    Fan, Jiayi
    Lee, JangHyeon
    Lee, YongKeun
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (14):
  • [10] Brain MRI image classification based on transfer learning and support vector machine
    Li, Zimeng
    Zhao, Yan
    Wang, Shigang
    [J]. OPTOELECTRONIC IMAGING AND MULTIMEDIA TECHNOLOGY VI, 2019, 11187