Utilize este identificador para referenciar este registo: https://hdl.handle.net/1822/88994

TítuloBenchmarking deep learning models and hyperparameters for bridge defects classification
Autor(es)Shahrabadi, Somayeh
Gonzalez, Dibet
Sousa, Nuno
Adão, Telmo
Peres, Emanuel
Magalhães, Luís Gonzaga Mendes
Palavras-chaveBenchmarking
Bridge defects inspection
Convolutional neural networks
Deep learning
Learning rate
Objective function optimization
Transfer learning
Data1-Jan-2023
Resumo(s)Deep learning (DL) is becoming increasingly popular in numerous application fields within the current Fourth Industrial Revolution (4IR) era. This is mainly due to its capability for providing accurate predictions and reliable consistency in decision-making. Bridge engineering focused on structure monitoring and inspection is a crucial activity for disaster prevention. Therefore, it is an application field wherein synergies between professional knowledge and sophisticated machine-based analytics strategies can be established and even drive time-effective interventions. This paper presents a comparison of DL models used to detect defects in bridges, resorting to the following architectures: MobileNetV2, Xception, InceptionV3, NASNetMobile, Visual Geometry Group Network-16 (VGG16), and InceptionResNetV2. Different optimizers (e.g., Nadam, Adam, RMSprop, and SGD) crossed with distinct learning rates (e.g., 1, 10-1, 10-2, 10-3, 10-4, and 10-5) were employed. VGG16, Xception, and NASNetMobile showed the most stable learning curves. Moreover, Gradient-weighted Class Activation Mapping (Grad-CAM) overlapping images clarifies that InceptionResNetV2 and InceptionV3 models seek features outside the areas of interest (defects). Comparing optimizers performance, the adaptive ones outperform SGD with decay schedulers for learning rates.
TipoArtigo em ata de conferência
URIhttps://hdl.handle.net/1822/88994
DOI10.1016/j.procs.2023.01.299
Arbitragem científicayes
AcessoAcesso restrito UMinho
Aparece nas coleções:CAlg - Artigos em livros de atas/Papers in proceedings

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
1-s2.0-S1877050923003083-main.pdf
Acesso restrito!
1,24 MBAdobe PDFVer/Abrir

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID