AI-based prediction of independent construction safety outcomes from universal attributes

Baker, Henrietta; Hallowell, Matthew R.; Tixier, Antoine J.‐P.

doi:10.1016/j.autcon.2020.103146

Cited by 76 publications

(62 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some examples, the system monitors the movements of workers and plant and their locations, analyses the potential for accidentsfor example, collisionsand informs the workers or issues instructions of what to do to prevent the accident (Andolfo and Sadeghpour, 2015). Other systems gather and analyse data from accident reports, search for patterns and produce information and, increasingly, recommendations on how to alter (or use) those patterns to achieve specific objectives and outcomes (Baker et al, 2019). Still further systems monitor performance and behaviours and produce recommendations and instructions for behavioural modification to maximise productivity and efficiency.…”

Section: Some Issuesmentioning

confidence: 99%

“…Whatever the philosophical difficulties and technical complications of programming any type of ethic into AI systems, weak or strong, the starting point is always with the designer/ developer of the system and to some extent the client and investors in the project. Assuming beneficent intent is not enough to view the project as simply a technical challenge to meet the client specificationsfor example, how to build an accidentprevention system through the collection and analysis of data (Baker et al, 2019).…”

Section: Towards Solutionsmentioning

confidence: 99%

“…The Baker et al (2019) model is designed to augment human decision making, and it is recognised that further work is required to determine the extent to which this method does improve that decision making. However, as discussed, the good intentions of the client and the best efforts of the designer give no assurance as to how the AI system can or will be used by misinformed, incompetent or malicious end users, nor can they be a guarantee of acceptance by a workforce suspicious of employers' intent and conscious of the potential to limit autonomy.…”

Section: Towards Solutionsmentioning

confidence: 99%

See 2 more Smart Citations

Moral responsibility and action in the use of artificial intelligence in construction

McAleenan¹

2020

Proceedings of the Institution of Civil Engineers - Management,

View full text Add to dashboard Cite

Rapid increases in processing power and speed of computing coupled with development of self-learning algorithms capable of autonomous decision making are central to current technological developments. This has fed dystopian visions of either out-of-control robots malevolently destroying humanity or benevolent robots enslaving humanity as a result of acting for its own good. A more nuanced assessment demonstrates that inherent in any benevolent intent is the unintended potential for harm, which must be addressed in parallel with if not in advance of developments in the field. This paper examines the hazards and challenges presented by artificial intelligence in respect of construction. In conjunction with developments and guidelines on machine ethics, it outlines the issues and posits how they may be addressed by governments, designers, contractors and worker organisations to access the growth potential of the sector as a socially responsible industry. 166 Cite this article McAleenan P (2020) Moral responsibility and action in the use of artificial intelligence in construction.

show abstract

Section: Some Issuesmentioning

confidence: 99%

Section: Towards Solutionsmentioning

confidence: 99%

Section: Towards Solutionsmentioning

confidence: 99%

See 1 more Smart Citation

Moral responsibility and action in the use of artificial intelligence in construction

McAleenan¹

2020

Proceedings of the Institution of Civil Engineers - Management,

View full text Add to dashboard Cite

show abstract

“…In recent years, construction automation has been effectively brought out through Artificial Intelligence (AI). AI has been employed for planning [25], safety management [26,27], construction management [28], automatic analysis of injury reports [29], automatic clustering of construction project documents based on textual similarity [30] and retrieval of Computer Aided Design (CAD) drawings [31]. Text mining (TM) is a widespread AI technology that uses Natural Language Processing (NLP) to transform unstructured documents into normalised, structured data for information retrieval, data mining, machine learning, statistics, and computational linguistics [32].…”

Section: Introductionmentioning

confidence: 99%

Understanding Construction Site Safety Hazards Through Open Data: Text Mining Approach

Rupasinghe

Panuwatwanich

2021

AEJ

View full text Add to dashboard Cite

Construction is an industry well known for its very high rate of injuries and accidents around the world. Even though many researchers are engaged in analysing the risks of this industry using various techniques, construction accidents still require much attention in safety science. According to existing literature, it has been found that hazards related to workers, technology, natural factors, surrounding activities and organisational factors are primary causes of accidents. Yet, there has been limited research aimed to ascertain the extent of these hazards based on the actual reported accidents. Therefore, the study presented in this paper was conducted with the purpose of devising an approach to extract sources of hazards from publicly available injury reports by using Text Mining (TM) and Natural Language Processing (NLP) techniques. This paper presents a methodology to develop a rule-based extraction tool by providing full details of lexicon building, devising extraction rules and the iterative process of testing and validation. In addition, the developed rule-based classifier was compared with, and found to outperform, the existing statistical classifiers such as Support Vector Machine (SVM), Kernel SVM, K-nearest neighbours, Naïve Bayesian classifier and Random Forest classifier. The finding using the developed tool identified the worker factor as the highest contributor to construction site accidents followed by technological factor, surrounding activities, organisational factor, and natural factor (1%). The developed tool could be used to quickly extract the sources of hazards by converting largely available unstructured digital accident data to structured attributes allowing better data-driven safety management.

show abstract

“…Many AEC researchers now use different CMs to shed light on some of the "wicked" problems that have bedevilled the industry and have attempted to unearth solutions to these problems (Maqsood et al, 2003). Most significant is the use of structural equation modelling (SEM), computer simulations and machine learning (ML) which has gained considerable embrace among AEC researchers (Akanmu et al, 2020;Alizadeh and Yitmen, 2018;Baker et al, 2020;Cheng et al, 2020;Zhao et al, 2019) in most developed and some developing countries.…”

Section: Introductionmentioning

confidence: 99%

High-performance computing for computational modelling in built environment-related studies – a scientometric review

Aghimien

Petinrin

et al. 2020

JEDT

View full text Add to dashboard Cite

Purpose This paper aims to present the result of a scientometric analysis conducted using studies on high-performance computing in computational modelling. This was done with a view to showcasing the need for high-performance computers (HPC) within the architecture, engineering and construction (AEC) industry in developing countries, particularly in Africa, where the use of HPC in developing computational models (CMs) for effective problem solving is still low. Design/methodology/approach An interpretivism philosophical stance was adopted for the study which informed a scientometric review of existing studies gathered from the Scopus database. Keywords such as high-performance computing, and computational modelling were used to extract papers from the database. Visualisation of Similarities viewer (VOSviewer) was used to prepare co-occurrence maps based on the bibliographic data gathered. Findings Findings revealed the scarcity of research emanating from Africa in this area of study. Furthermore, past studies had placed focus on high-performance computing in the development of computational modelling and theory, parallel computing and improved visualisation, large-scale application software, computer simulations and computational mathematical modelling. Future studies can also explore areas such as cloud computing, optimisation, high-level programming language, natural science computing, computer graphics equipment and Graphics Processing Units as they relate to the AEC industry. Research limitations/implications The study assessed a single database for the search of related studies. Originality/value The findings of this study serve as an excellent theoretical background for AEC researchers seeking to explore the use of HPC for CMs development in the quest for solving complex problems in the industry.

show abstract

AI-based prediction of independent construction safety outcomes from universal attributes

Cited by 76 publications

References 25 publications

Moral responsibility and action in the use of artificial intelligence in construction

Moral responsibility and action in the use of artificial intelligence in construction

Understanding Construction Site Safety Hazards Through Open Data: Text Mining Approach

High-performance computing for computational modelling in built environment-related studies – a scientometric review

Contact Info

Product

Resources

About