Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/219672
DC FieldValue
dc.titleFACADE DEFECTS CLASSIFICATION FROM IMAGE DATASET USING DEEP LEARNING
dc.contributor.authorJIA LUYAO
dc.date.accessioned2020-06-07T11:12:24Z
dc.date.accessioned2022-04-22T15:39:28Z
dc.date.available2020-06-15
dc.date.available2022-04-22T15:39:28Z
dc.date.issued2020-06-07
dc.identifier.citationJIA LUYAO (2020-06-07). FACADE DEFECTS CLASSIFICATION FROM IMAGE DATASET USING DEEP LEARNING. ScholarBank@NUS Repository.
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/219672
dc.description.abstractDefects inspection conducted for buildings is a compulsory work in reality. With the development of technology, it is necessary to find a method to increase the productivity and efficiency of inspection works. Artificial Intelligence (AI) has been very popular in the construction industry and Machine Learning (ML) is one element of it. ML consists of a subset called Deep Learning (DL) which has a strength of automatic classification through input data and learning complex functions. Thus, applying DL in facade defects classification is an excellent method and this method has to be based in 2D images for easy operation. Image data collection is done by taking images for facade defects of public housing in Singapore. In DL, the Convolutional Neural Network (CNN) is the most common and efficient algorithm for image applications. Moreover, the Visual Geometry Group with 16 layers (VGG-16) network which is a systemic CNN model as a pre-trained model and incorporates a transfer learning: Fine-Tuning method to develop the classification model to train 20,909 images and test 350 images per epoch. The model will output the accuracy and loss results, plot out the normalised confusion matrix and the receiver operating characteristics (ROC) curves for analysis.
dc.language.isoen
dc.sourcehttps://lib.sde.nus.edu.sg/dspace/handle/sde/4841
dc.subjectDeep Learning (DL)
dc.subjectFine-Tuning method
dc.subjectVisual Geometry Group with 16 layers (VGG-16) network
dc.subjectConvolutional Neural Network (CNN)
dc.subjectBuilding
dc.subjectPFM
dc.subjectProject and Facilities Management
dc.subjectWang Qian
dc.subject2019/2020 PFM
dc.typeDissertation
dc.contributor.departmentBUILDING
dc.contributor.supervisorWANG QIAN
dc.description.degreeBachelor's
dc.description.degreeconferredBACHELOR OF SCIENCE (PROJECT AND FACILITIES MANAGEMENT)
dc.embargo.terms2020-06-15
Appears in Collections:Bachelor's Theses

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Jia Luyao 2019-2020_dissertation.pdf24.99 MBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

63
checked on Dec 1, 2022

Download(s)

33
checked on Dec 1, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.