Review
Artificial intelligence in the AEC industry: Scientometric analysis and visualization of research activities

https://doi.org/10.1016/j.autcon.2020.103081Get rights and content

Highlights

  • Genetic algorithms, neural networks, fuzzy logic, fuzzy sets, and machine learning are the most widely used AI methods in AEC.

  • Optimization, simulation, uncertainty, project management, and bridges are the most commonly addressed topics/issues using AI methods/concepts.

  • Future research opportunities lie in applying robotic automation to AEC problems.

  • There are future research opportunities also in using convolutional neural networks (CNNs) for solving AEC problems.

Abstract

The Architecture, Engineering and Construction (AEC) industry is fraught with complex and difficult problems. Artificial intelligence (AI) represents a powerful tool to assist in addressing these problems. Therefore, over the years, researchers have been conducting research on AI in the AEC industry (AI-in-the-AECI). In this paper, the first comprehensive scientometric study appraising the state-of-the-art of research on AI-in-the-AECI is presented. The science mapping method was used to systematically and quantitatively analyze 41,827 related bibliographic records retrieved from Scopus. The results indicated that genetic algorithms, neural networks, fuzzy logic, fuzzy sets, and machine learning have been the most widely used AI methods in AEC. Optimization, simulation, uncertainty, project management, and bridges have been the most commonly addressed topics/issues using AI methods/concepts. The primary value and uniqueness of this study lies in it being the first in providing an up-to-date inclusive, big picture of the literature on AI-in-the-AECI. This study adds value to the AEC literature through visualizing and understanding trends and patterns, identifying main research interests, journals, institutions, and countries, and how these are linked within now-available studies on AI-in-the-AECI. The findings bring to light the deficiencies in the current research and provide paths for future research, where they indicated that future research opportunities lie in applying robotic automation and convolutional neural networks to AEC problems. For the world of practice, the study offers a readily-available point of reference for practitioners, policy makers, and research and development (R&D) bodies. This study therefore raises the level of awareness of AI and facilitates building the intellectual wealth of the AI area in the AEC industry.

Introduction

Artificial intelligence (AI) is playing a core role in the Fourth Industrial Revolution (Industry 4.0), i.e., the digitalization era, wherein intelligent systems and technologies are used to create an active connection between the physical and virtual (digital) worlds. AI denotes the science and engineering of creating intelligent machines that exhibit reasoning, learning, knowledge, communication, perception, planning, and the ability to move and operate objects [1]. It has several benefits that have been widely documented in the literature. For instance, it can use sophisticated algorithms to “learn” from “big” data, and then use the knowledge gained to assist industry/practice [2]. Moreover, AI provides vast opportunities for significant productivity improvements via analyzing large volumes of data quickly and accurately [3]. Additionally, AI systems and technologies can tackle complicated, nonlinear practical problems and, once trained, could undertake predictions and generalizations at high speed [4].

Because of these benefits, AI has attracted substantial attention within a wide range of industries, including Architecture, Engineering and Construction (AEC) [4], capturing the attention of AEC researchers. This has resulted in an upsurge in the number of research works and publications on AI in the AEC industry (AI-in-the-AECI) [5]. This situation presents danger, as it makes it tough to grasp the status quo of the knowledge body, posing a major risk of neglecting essential areas and questions for research and practice improvement [6]. To address this scientific problem, undertaking a rigorous review and analysis of the domain is necessary.

Previous review studies in this area [[7], [8], [9], [10]] have made valuable contributions. Nonetheless, they have some limitations. First, they have been qualitative and based on manual appraisals. Thus, they may be significantly impacted by subjective biases, lack of reproducibility, and reduced reliability [11]. Ref. [12] indicated that manual reviews examine the “trees”, but do not provide a broad overview of the “forest”. Second, existing review studies have had narrowed perspectives, focusing on limited applications or on specific AI methods. For example, Ref. [10] focused on “big” data technologies application in the AEC industry; while Ref. [9] focused on automation in construction scheduling. Ref. [13] recently published a bibliometric study of engineering applications of AI. However, their study is limited to only the publications in one single journal and gives an overview of what has already been done without providing directions for future work. In the light of these facts, these review studies do not afford a full picture of the state-of-the-art of research on AI-in-the-AECI. In fact, a study that offers a complete picture and understanding of the AI literature in the specific domain of AEC is still missing.

As an attempt to fill this gap, the present review study stands out, being the first to comprehensively survey the intellectual core and the landscape of the general body of knowledge on AI-in-the-AECI using a quantitative technique. This study contributes to the field in several ways by: identifying the scope and assessing the quality of the existing body of knowledge; detecting omissions and deficiencies; and determining where best to focus future research efforts. In practical terms, the study serves as a valuable and up-to-date reference point for enhancing the knowledge of policy makers and practitioners and assisting them in planning and funding efforts regarding adopting AI-in-the-AECI.

Section snippets

Research methodology

The present study used the science mapping method to analyze the literature on AI-in-the-AECI. Science mapping, “a generic process of domain analysis and visualization” [14], aims at detecting the intellectual structure of a scientific domain. This method is helpful for visualizing significant patterns and trends in a large body of literature and bibliographic data [15]. It allows researchers to make literature-related discoveries that would not be possible through other methods [16]. A science

Trend of research on AI-in-the-AECI: the 20th and the 21st centuries

The AI research field in general was born in 1956; whereas the first study on AI-in-the-AECI appears to be Ref. [30]'s work, published in the Computer-Aided Design journal, where computer applications to architecture were studied. This implies that research regarding AI-in-the-AECI has been around since the 1970s. Fig. 1 shows the trend in research publications on AI-in-the-AECI from 1974 to 2019. It reveals a steady and gradual increase in interest in research about AI-in-the-AECI from 1974

Discussion and future directions

During the last few decades, there has been a growing interest in research applying AI techniques/algorithms/concepts to AEC problems. This activity has been thoroughly reviewed in this study through quantitative, text-mining approaches. The review has been conducted to identify clusters and collaboration networks of the main research interests (including various AI methods/concepts as well as various AEC topics/issues addressed using AI methods/concepts), journals, institutions, and countries

Theoretical and practical contributions

AI deals with the science of inventing intelligent machines and computer systems that can learn and help to solve problems. It is playing a significant role in Industry 4.0, the era of digitalization, driving the digital transformation of many industries, including AEC. In the AEC industry, AI provides advantages to deal with a diversity of difficult, complex engineering and management problems that defy conventional computational methods-based solutions. Consequently, over the past few

Declaration of competing interest

The authors declare no conflict of interest.

Acknowledgements

The authors gratefully acknowledge the Department of Building and Real Estate of The Hong Kong Polytechnic University for funding this research. Special appreciations also go to the Editors and Reviewers whose constructive and invaluable comments and suggestions played a decisive role in significantly improving the quality of this work.

References (117)

  • C.M. Eastman

    Through the looking glass: why no wonderland: computer applications to architecture in the USA

    Comput. Aided Des.

    (1974)
  • M.S. El-Abbasy et al.

    MOSCOPEA: multi-objective construction scheduling optimization using elitist non-dominated sorting genetic algorithm

    Autom. Constr.

    (2016)
  • Z.S. Chen et al.

    Fostering linguistic decision-making under uncertainty: a proportional interval type-2 hesitant fuzzy TOPSIS approach based on Hamacher aggregation operators and andness optimization models

    Inf. Sci.

    (2019)
  • Y. Deng et al.

    3D simulation of deflection basin of pavements under high-speed moving loads

    Constr. Build. Mater.

    (2019)
  • H. Salehi et al.

    Emerging artificial intelligence methods in structural engineering

    Eng. Struct.

    (2018)
  • M. Marzouk et al.

    BIM-based approach for optimizing life cycle costs of sustainable buildings

    J. Clean. Prod.

    (2018)
  • R. Toledo et al.

    Shape design optimization of road acoustic barriers featuring top-edge devices by using genetic algorithms and boundary elements

    Engineering Analysis with Boundary Elements

    (2016)
  • Y. Zou et al.

    A review of risk management through BIM and BIM-related technologies

    Saf. Sci.

    (2017)
  • P.J. Rousseeuw

    Silhouettes: a graphical aid to the interpretation and validation of cluster analysis

    J. Comput. Appl. Math.

    (1987)
  • J. Huyan et al.

    Detection of sealed and unsealed cracks with complex backgrounds using deep convolutional neural network

    Autom. Constr.

    (2019)
  • W. Fang et al.

    Falls from heights: a computer vision-based approach for safety harness detection

    Autom. Constr.

    (2018)
  • A. Serenko

    The development of an AI journal ranking based on the revealed preference approach

    Journal of Informetrics

    (2010)
  • Y. Ding

    Scientific collaboration and endorsement: network analysis of coauthorship and citation networks

    Journal of Informetrics

    (2011)
  • J. Gu et al.

    Recent advances in convolutional neural networks

    Pattern Recogn.

    (2018)
  • Y. Wei et al.

    A vision and learning-based indoor localization and semantic mapping framework for facility operations and management

    Autom. Constr.

    (2019)
  • J. Wu et al.

    Automatic detection of hardhats worn by construction personnel: a deep learning approach and benchmark dataset

    Autom. Constr.

    (2019)
  • J. McCarthy, The inversion of functions defined by turing machines, in: C.E. Shannon, J. McCarthy (Eds.), Automata...
  • F. Jiang et al.

    Artificial intelligence in healthcare: past, present and future

    Stroke and Vascular Neurology

    (2017)
  • K.M. El-Gohary et al.

    Engineering approach using ANN to improve and predict construction labor productivity under different influences

    J. Constr. Eng. Manag.

    (2017)
  • M.R. Hosseini et al.

    Analysis of citation networks in building information modeling research

    J. Constr. Eng. Manag.

    (2018)
  • R.E. Levitt et al.

    Artificial intelligence techniques for generating construction project plans

    J. Constr. Eng. Manag.

    (1988)
  • V. Faghihi et al.

    Automation in construction scheduling: a review of the literature

    Int. J. Adv. Manuf. Technol.

    (2015)
  • D. Yu et al.

    Visualization and quantitative research on intuitionistic fuzzy studies

    Journal of Intelligent & Fuzzy Systems

    (2016)
  • C. Chen

    Science mapping: a systematic review of the literature

    Journal of Data and Information Science

    (2017)
  • M.J. Cobo et al.

    Science mapping software tools: review, analysis, and cooperative study among tools

    J. Am. Soc. Inf. Sci. Technol.

    (2011)
  • H.N. Su et al.

    Mapping knowledge structure by keyword co-occurrence: a first look at journal papers in technology foresight

    Scientometrics

    (2010)
  • W. Hood et al.

    The literature of bibliometrics, scientometrics, and informetrics

    Scientometrics

    (2001)
  • N.J. van Eck, L. Waltman, VOSviewer manual: manual for VOSviewer version 1.6.11,...
  • M. Bastian, S. Heymann, M. Jacomy, Gephi: an open source software for exploring and manipulating networks, Proceedings...
  • C. Chen, CiteSpace Manual, http://cluster.ischool.drexel.edu/~cchen/citespace/CiteSpaceManual.pdf, (2014) Accessed 18th...
  • Gephi, Gephi tutorial quick start, https://gephi.org/users/quick-start/, (2017) Accessed 18th Sep...
  • X. Zhao et al.

    A bibliometric review of green building research 2000–2016

    Archit. Sci. Rev.

    (2018)
  • L.I. Meho et al.

    Citation counting, citation ranking, and h-index of human-computer interaction researchers: a comparison of Scopus and web of science

    J. Am. Soc. Inf. Sci. Technol.

    (2008)
  • R. Shrivastava et al.

    Artificial intelligence research in India: a scientometric analysis

    Sci. Technol. Libr.

    (2016)
  • M.F. Rooney, S.E. Smith, Artificial intelligence in simple beam design, J. Struct. Div. 108 (10) (1982) 2344–2348,...
  • S.A. Oke, A literature review on artificial intelligence, Int. J. Inf. Manag. Sci. 19 (4) (2008) 535–570,...
  • Internet Society, Internet society global internet report: paths to our digital future,...
  • National Research Council

    Funding a Revolution: Government Support for Computing Research

    (1999)
  • N.J. van Eck et al.

    Visualizing bibliometric networks

  • The Constructor, 23 types of concrete used in construction and their applications,...
  • Cited by (298)

    View all citing articles on Scopus
    View full text