Deep Learning-Based Applications for Safety Management in the AEC Industry: A Review

Hou, Lei; Chen, Haosen; Zhang, Kevin; Wang, Xiangyu

doi:10.3390/app11020821

Cited by 42 publications

(24 citation statements)

References 132 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5, Automation in Construction, Journal of Computing in Civil Engineering, and Journal of Construction Engineering and Management were among the most influential journals that had been contributing to the research community of machine learning in construction management. This finding was further supported by the statistics in Table 3, there were 25 articles published in the Automation in Construction had an outstanding performance, receiving the publications (25) and citations (557), occupying the first position in this topic research. Followed by the Journal of Computing in Civil Engineering with 14 papers (86 citations) and the Journal of Construction Engineering and Management with 12 papers (176 citations) on this domain.…”

Section: Science Mapping Of Academic Journalssupporting

confidence: 63%

“…Hence, construction safety is a top priority on all job sites, and machine learning offers a high-tech solution to this problem. That is why applying machine learning in construction safety has been attracted numerous researches to date [8,14,[19][20][21][22][23][24][25][26][27][28]. In the study [21], neural network and decision tree analyses were implemented to assess the unsafe act of not anchoring harnesses while working on a scaffold of 40 migrant workers, whereas, with an accident data from the Singapore construction industry, a neural network analysis was performed on a quantitative occupational safety and health management system audit [22].…”

Section: B Safety Management For Construction Sitesmentioning

confidence: 99%

See 1 more Smart Citation

Research Trends on Machine Learning in Construction Management: A Scientometric Analysis

Van

Quoc

2021

JASTT

View full text Add to dashboard Cite

Machine learning plays a vital role in construction industry which could make improve project’s safety, productivity, and quality. Many studies have attempted to explore the potential opportunities to adopt this technology in different aspects of the construction sector. However, no comprehensive study to review the global research trends on this technological advancement in construction management domain. The goal is to investigate and summarize the state-of-the-art knowledge body in this topic in a systematic manner. To achieve this, this paper considered 161 studies on machine learning in construction management related to bibliographic records retrieved from the Scopus database by adopting scientometric analysis approach. This paper found that since 2014, there has been a considerable increase in the number of publications on this domain. Researchers from the United States, China, and Australia have been the main contributors to this research area through regional analysis. This study also revealed that approximately 34% of all countries in the world are engaged in this domain research. In addition, five main aspects in construction management have been applied machine learning techniques, namely, assess and reduce risk, safety management for construction sites, cost estimation and prediction, Schedule management, and building energy demand prediction. Furthermore, three potential construction management research areas that can apply this technology were proposed for further studies. The findings will help both professionals and researchers more understanding how machine learning knowledge is evolving and its role played in the construction management domain, and this study thus offers a useful reference point to how can develop this area in the future.

show abstract

Section: Science Mapping Of Academic Journalssupporting

confidence: 63%

Section: B Safety Management For Construction Sitesmentioning

confidence: 99%

Research Trends on Machine Learning in Construction Management: A Scientometric Analysis

Van

Quoc

2021

JASTT

View full text Add to dashboard Cite

show abstract

“…In the vast majority of bibliometric analyses and articles, US scholars are consistently ranked first in total articles numbers and total citation frequencies. The total articles and total citation frequencies from UK scholars often ranked second [53][54][55][56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72].…”

Section: Productive Regions/countriesmentioning

confidence: 99%

Science Mapping: A Scientometric Review on Resource Curses, Dutch Diseases, and Conflict Resources during 1993–2020

Wong

2021

Energies

View full text Add to dashboard Cite

Over the past few decades, the wealth of Africa has not made African wealthy. There is a voicing that Africa is cursed, whether richly poor or poorly rich. Sub-Saharan Africa is commonplace for political turbulence, as well as humanitarian and economic misery. In such a catastrophic situa-tion, political economics studies have focused on the Resource Curses, Dutch Diseases, and Con-flict Resources in this area. A systematic scientometric analysis of this field would be beneficial but is currently lacking in the academic literature. Using VOSviewer and CiteSpace, this review fills the void by analyzing the 1783 articles published in the WoS SSCI Collection between 1993 and 2020 on the “Resource Curses”, “Dutch Diseases”, and “Conflict Resources”. The author dis-cusses recent papers with disruptive potential, references with the most robust citation explora-tions, and cooperation networks between authors and institutes. Three hotspots were detected: the causes and effects of the Resource curses; the interaction among the Resource Curses, Dutch Diseases, and Conflict Resources; the factors that affect rent collection and regime resilience. While the literature on the “Resource curse” and “Dutch Disease” has been around longer, studies on “Conflict Resources” are picking up quickly. Conflict Resources were characterized by active citation exploration keywords and multiple active co-citation clusters, including possibly groundbreaking articles. There is a massive overlap between the three strings of literature, but each one has its emphasis.

show abstract

“…The above previous studies prove the potential of assisting platforms (especially, adopting building information models or deep learning-based method) in facilitating automatic risk identification in deep excavation projects [15]. However, these previous studies on assisting platforms are often based on proprietary geometric modeling kernels and data storage formats, which hinder their semantic interoperability with other software applications (e.g., BIM design software) [10,11].…”

Section: Literature Review 21 Construction Risk Identification-related Assisting Platformsmentioning

confidence: 99%

Semantic IFC Data Model for Automatic Safety Risk Identification in Deep Excavation Projects

2021

View full text Add to dashboard Cite

Safety risk identification throughout deep excavation construction is an information-intensive task, involving construction information scattered in project planning documentation and dynamic information obtained from different field sensors. However, inefficient information integration and exchange have been an important obstacle to the development of automatic safety risk identification in actual applications. This research aims to achieve the requirements for information integration and exchange by developing a semantic industry foundation classes (IFC) data model based on a central database of Building Information Modeling (BIM) in dynamic deep excavation process. Construction information required for risk identification in dynamic deep excavation is analyzed. The relationships among construction information are identified based on the semantic IFC data model, involved relationships (i.e., logical relationships and constraints among risk events, risk factors, construction parameters, and construction phases), and BIM elements. Furthermore, an automatic safety risk identification approach is presented based on the semantic data model, and it is tested through a construction risk identification prototype established under the BIM environment. Results illustrate the effectiveness of the BIM-based central database in accelerating automatic safety risk identification by linking BIM elements and required construction information corresponding to the dynamic construction process.

show abstract

Deep Learning-Based Applications for Safety Management in the AEC Industry: A Review

Cited by 42 publications

References 132 publications

Research Trends on Machine Learning in Construction Management: A Scientometric Analysis

Research Trends on Machine Learning in Construction Management: A Scientometric Analysis

Science Mapping: A Scientometric Review on Resource Curses, Dutch Diseases, and Conflict Resources during 1993–2020

Semantic IFC Data Model for Automatic Safety Risk Identification in Deep Excavation Projects

Contact Info

Product

Resources

About