Variable Selection from Image Texture Feature for Automatic Classification of Concrete Surface Voids.

Simple item page
dc.citation.issue1
dc.citation.volume2021
dc.contributor.authorZhao Z
dc.contributor.authorLiu T
dc.contributor.authorZhao X
dc.contributor.editorHaber RE
dc.coverage.spatialUnited States
dc.date.accessioned2024-10-09T01:55:09Z
dc.date.available2024-10-09T01:55:09Z
dc.date.issued2021-03-08
dc.description.abstractMachine learning plays an important role in computational intelligence and has been widely used in many engineering fields. Surface voids or bugholes frequently appearing on concrete surface after the casting process make the corresponding manual inspection time consuming, costly, labor intensive, and inconsistent. In order to make a better inspection of the concrete surface, automatic classification of concrete bugholes is needed. In this paper, a variable selection strategy is proposed for pursuing feature interpretability, together with an automatic ensemble classification designed for getting a better accuracy of the bughole classification. A texture feature deriving from the Gabor filter and gray-level run lengths is extracted in concrete surface images. Interpretable variables, which are also the components of the feature, are selected according to a presented cumulative voting strategy. An ensemble classifier with its base classifier automatically assigned is provided to detect whether a surface void exists in an image or not. Experimental results on 1000 image samples indicate the effectiveness of our method with a comparable prediction accuracy and model explicable.
dc.description.confidentialfalse
dc.edition.editionJanuary 2021
dc.format.pagination5538573-
dc.identifier.author-urlhttps://www.ncbi.nlm.nih.gov/pubmed/33747071
dc.identifier.citationZhao Z, Liu T, Zhao X. (2021). Variable Selection from Image Texture Feature for Automatic Classification of Concrete Surface Voids.. Comput Intell Neurosci. 2021. 1. (pp. 5538573-).
dc.identifier.doi10.1155/2021/5538573
dc.identifier.eissn1687-5273
dc.identifier.elements-typejournal-article
dc.identifier.issn1687-5265
dc.identifier.number5538573
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/71651
dc.languageeng
dc.publisherHindawi Limited
dc.publisher.urihttps://onlinelibrary.wiley.com/doi/10.1155/2021/5538573
dc.relation.isPartOfComput Intell Neurosci
dc.rights(c) 2021 The Author/s
dc.rightsCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectAlgorithms
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.titleVariable Selection from Image Texture Feature for Automatic Classification of Concrete Surface Voids.
dc.typeJournal article
pubs.elements-id488947
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Published version.pdf
Size:
2.4 MB
Format:
Adobe Portable Document Format
Description:
488947 PDF.pdf
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
9.22 KB
Format:
Plain Text
Description:
Download
Collections
Journal Articles