Classification of major construction materials in construction environments using ensemble classifiers

Son, Hyojoo; Kim, Changmin; Hwang, Nahyae; Kang, Youngcheol

doi:10.1016/j.aei.2013.10.001

Cited by 61 publications

(27 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The vision-based monitoring systems have been used in previous studies to monitor target objects for various purposes such as progress monitoring [12,14,16,31,32,[38][39][40][41][42], productivity analysis [8,18,20,26,43], safety management [24,[44][45][46][47][48][49], facility condition assessment [13,[50][51][52][53][54][55][56][57][58], and monitoring technology used on a construction site [10,19,21,22,[27][28][29][59][60][61][62][63][64]. Most of the studies have one or two recognizable object classes.…”

Section: Previous Vision-based Monitoring System Recognizing Objects mentioning

confidence: 99%

Data-driven scene parsing method for recognizing construction site objects in the whole image

Kim

2016

Automation in Construction

View full text Add to dashboard Cite

Section: Previous Vision-based Monitoring System Recognizing Objects mentioning

confidence: 99%

Data-driven scene parsing method for recognizing construction site objects in the whole image

Kim

2016

Automation in Construction

View full text Add to dashboard Cite

“…Figure 3 shows the result of the region-of-interest (ROI) detection from the registered 3D point cloud. In this case, 3D points corresponding to concrete structures were targeted and detected by employing the ensemble classifier proposed by Son et al [18]. Through this process, the stacked materials and fence having different color values from the concrete structures, were distinguished and discarded.…”

Section: Methodsmentioning

confidence: 99%

“…In order to distinguish 3D points of the corresponding building elements to be modeled, structural elements in this case, an ensemble classifier proposed by Son et al [18] was employed. This method uses a color value as a feature to distinguish ROI from laser-scan data.…”

Section: Region-of-interest (Roi) Detectionmentioning

confidence: 99%

Semantic AsBuilt 3D Modeling of Buildings Under Construction from Laser-Scan Data Based on Local Convexity without an As-Planned Model

Son¹,

Na²,

Kim³

2015

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

Self Cite

View full text Add to dashboard Cite

As-built building information models (BIMs) need to be represented with the composing building elements having their own functional semantic information. In order to generate such as-built BIMs with composing building elements, it is necessary to recognize each of the semantic elements and separate them from each other. In addition, the as-built BIM needs to be generated and updated during or after each major construction activity because most of the structural elements and nonstructural elements (especially for mechanical, electrical, and plumbing (MEP) components) are covered by other objects as the construction phase progresses. This study aims to propose a method for generating a semantic as-built BIM from laser-scan data acquired during the construction phase, especially for structural works. A field experiment was performed to validate the proposed method by acquiring and processing laserscan data from the construction site. The experimental result shows that the proposed method can be used for semantic as-built BIMs without any prior information from as-planned models.

show abstract

“…This study carried out 10-fold cross validation to evaluate the classification performance of the six classifier models. This method is known to minimize bias and variance compared to all other validation methods [33,34]. In 10-fold cross validation, the training dataset was divided into ten subsets.…”

Section: Performance Evaluation Measuresmentioning

confidence: 99%

Comparison of Single Classifier Models for Predicting Long-term Business Failure of Construction Companies Using Finance-based Definition of the Failure

Choi¹,

Son²,

Kim³

et al. 2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

Self Cite

View full text Add to dashboard Cite

This study compares the performance of six classifier models (ANN, KNN, C4.5, SVM, LR, and NB) for predicting the business failure of construction companies after three years from 2010 to 2012. Although previous studies have explored numerous business failure prediction models for construction companies, these models have focused on short-term failure, defined as failure occurring within one year, and have defined business failure based on companies' experiencing serious legal events, including bankruptcy, delisting, and default. However, the construction industry is typically characterized by projects with longer durations, usually exceeding one year. This implies that previous short-term models cannot predict the business failure of construction companies until the end of particular projects. Moreover, this problem is compounded by the fact that legal events can involve lengthy proceedings, which are often initiated much later than the actual moment of the business failure. Therefore, in this study, six classifier models will be used to predict the business failure of the construction companies within three years using a finance-based definition of failure. The results show that all six models' performances noticeably decrease when they predict more than one year. These results demonstrate that previous short-term prediction models with outstanding performance cannot be practical in predicting the long-term business failure of construction companies.

show abstract

Classification of major construction materials in construction environments using ensemble classifiers

Cited by 61 publications

References 60 publications

Data-driven scene parsing method for recognizing construction site objects in the whole image

Data-driven scene parsing method for recognizing construction site objects in the whole image

Semantic AsBuilt 3D Modeling of Buildings Under Construction from Laser-Scan Data Based on Local Convexity without an As-Planned Model

Comparison of Single Classifier Models for Predicting Long-term Business Failure of Construction Companies Using Finance-based Definition of the Failure

Contact Info

Product

Resources

About