Material Classification via Machine Learning Techniques: Construction Projects Progress Monitoring

Abstract

Nowadays, the construction industry is on a fast track to adopting digital processes under the Industrial Revolution (IR) 4.0. The desire to automate maximum construction processes with less human interference has led the industry and research community to inclined towards artificial intelligence. This chapter has been themed on automated construction monitoring practices by adopting material classification via machine learning (ML) techniques. The study has been conducted by following the structure review approach to gain an understanding of the applications of ML techniques for construction progress assessment. Data were collected from the Web of Science (WoS) and Scopus databases, concluding 14 relevant studies. The literature review depicted the support vector machine (SVM) and artificial neural network (ANN) techniques as more effective than other ML techniques for material classification. The last section of this chapter includes a python-based ANN model for material classification. This ANN model has been tested for construction items (brick, wood, concrete block, and asphalt) for training and prediction. Moreover, the predictive ANN model results have been shared for the readers, along with the resources and open-source web links.

Construction material classification on imbalanced datasets using Vision Transformer architecture (ViT)

“…Davis et al designed and described a deep CNN to identify seven typical Construction and Demolition Waste (C&DW) classi cations using digital images of waste deposited in a construction site bin [26]. Alaloul and Qureshi used an ANN model to classify some construction materials [5]. Accuracy:…”

“…Although there are several studies conducted in the area of material classi cation, the literature review reveals that there are some shortcomings that need to be addressed. Some of the previous studies were restricted to just one speci c material [10-13, 19, 20, 25] or a limited number of material categories [5,6,16,17,21,22]. Furthermore, some studies employed tiny datasets, that is to say, they contained few images [13].…”

“…For automatically monitoring construction progress or producing Building Information Models (BIM) from site images, material classi cation is a major step [3,4]. Digitalized material classi cation not only extracts the appearance-based information for automated project monitoring and control, but also helps with the segmentation of elements for the automated generation of 3D as-built models, such as the scan-to-BIM process [4][5][6].…”

“…Overall, automated material classi cation is a bene cial tool that is utilized for a broad range of construction applications. It can improve the performance output of various activities, including defect identi cation, on-site material control, and progress monitoring [5][6][7]. Moreover, material classi cation would increase the accuracy of building element recognition signi cantly.…”

Factors affecting the implementation of automated progress monitoring of rebar using vision-based technologies

“…The studies found photogrammetry, computer vision and ML as popular technologies for project progress and productivity monitoring. However, traditional procedures still have been adopted for various monitoring activities (Qureshi et al , 2022a; Alaloul and Qureshi, 2021).…”