Construction legal support for differing site conditions (DSC) through statistical modeling and machine learning (ML)

Mahfouz, Tarek

doi:10.31274/etd-180810-681

Cited by 4 publications

(4 citation statements)

References 114 publications

(105 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This 7 is the key reason that most of the existing work, presented in 8 subsequent subsections, has focused on data analytics rather 9 than Big Data is that the Big Data revolution-i.e., the ability 10 to process large amounts of diverse data on a large scale-has 11 only recently happened. Existing [31], learning from post-project reviews (PPRs) [32], decision 35 support for construction litigation [33], detecting structural 36 damages of buildings [34], identifying actions of workers and 37 heavy machinery [35], [36], etc., are to name a few.…”

mentioning

confidence: 99%

“…Although Big Data trend is gradually creeping in the industry; 6 its applicability is amplified further by many other emerging 7 trends such as BIM, IOT, cloud computing, smart buildings, 8 and augmented reality, which are also slightly elaborated. We [31] Learning from post project reviews (PPRs) -Link analysis -Dimensional matrix analysis [32] Decision support systems for construction litigation -Naïve Bayes -Decision trees -Rule inductive [33] Structural damage detection in buildings -Gaussian distribution -Monte Carlo simulation [34] Identifying workers and heavy machinery actions towards site safety -Gaussian distribution -Naïve Bayes -Bags of video feature [35], [36] TABLES 32 Expert system for optimal markup estimation -ANN [75] Genetic Algorithms (GA)…”

mentioning

confidence: 99%

See 1 more Smart Citation

Big Data in the construction industry: A review of present status, opportunities, and future trends

Bilal

Oyedele

Qadir

et al. 2016

Advanced Engineering Informatics

498

307

View full text Add to dashboard Cite

The ability to process large amounts of data and 1 to extract useful insights from data has revolutionised society. 2 This phenomenon-dubbed as Big Data-has applications for a 3 wide assortment of industries, including the construction industry. 4 The construction industry already deals with large volumes of 5 heterogeneous data; which is expected to increase exponentially 6 as technologies such as sensor networks and the Internet of 7 Things are commoditized. In this paper, we present a detailed 8 survey of the literature, investigating the application of Big Data 9 techniques in the construction industry. We reviewed related 10 works published in the databases of American Association of 11 Civil Engineers (ASCE), Institute of Electrical and Electronics 12 Engineers (IEEE), Association of Computing Machinery (ACM), 13 and Elsevier Science Direct Digital Library. While the application 14 of data analytics in the construction industry is not new, the 15 adoption of Big Data technologies in this industry remains at a 16 nascent stage and lags the broad uptake of these technologies in 17 other fields. To the best of our knowledge, there is currently no 18 comprehensive survey of Big Data techniques in the context of 19 the construction industry. This paper fills the void and presents a 20 wide-ranging interdisciplinary review of literature of fields such 21 as statistics, data mining and warehousing, machine learning, and 22 Big Data Analytics in the context of the construction industry. 23 We discuss the current state of adoption of Big Data in the 24 construction industry and discuss the future potential of such 25 technologies across the multiple domain-specific sub-areas of the 26 construction industry. We also propose open issues and directions 27 for future work along with potential pitfalls associated with Big 28 Data adoption in the industry. 29 I. INTRODUCTION 30 The world is currently inundated with data, with fast advanc-31 ing technology leading to its steady increase. Today, companies 32 deal with petabytes (10 15 bytes) of data. Google processes 33 above 24 petabytes of data per day [1], while Facebook gets 34 more than 10 million photos per hour [1]. The glut of data 35 increased in 2012 is approximately 2.5 quintillion (10 18) bytes 36 per day [2]. This data growth brings significant opportunities 37 to scientists for identifying useful insights and knowledge. 38 Arguably, the accessibility of data can improve the status 39 quo in various fields by strengthening existing statistical and 40 algorithmic methods [3], or by even making them redundant 41 [4]. 42 The construction industry is not an exception to the per-43 vasive digital revolution. The industry is dealing with sig-44 nificant data arising from diverse disciplines throughout the 45 life cycle of a facility. Building Information Modelling (BIM) 46 is envisioned to capture multi-dimensional CAD information 47 systematically for supporting multidisciplinary collaboration 48 among the stakeholders [5]. BIM data is typically 3D ge-49 ometric enc...

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Big Data in the construction industry: A review of present status, opportunities, and future trends

Bilal

Oyedele

Qadir

et al. 2016

Advanced Engineering Informatics

498

307

View full text Add to dashboard Cite

show abstract

“…SVM demonstrated good performance and has proven to be better than other models [2]. To estimate steel structure productivity, the researcher used the SVM development model technique and discovered that among the developed models, the Naive Bayes (NB) model was the most appropriate [3]. Using the current state of early planning as model inputs, the researcher developed artificial neural network ensemble and support vector machine classification models to predict project cost and schedule success.…”

Section: Literature Reviewmentioning

confidence: 99%

Archives of Civil Engineering

Hasan,

Hammody,

Albayati

2022

View full text Add to dashboard Cite

The cost overrun in road construction projects in Iraq is one of the major problems that face the construction of new roads. To enable the concerned government agencies to predict the final cost of roads, the objective this paper suggested is to develop an early cost estimating model for road projects using a support vector machine based on (43) sets of bills of quantity collected in Baghdad city in Iraq. As cost estimates are required at the early stages of a project, consideration was given to the fact that the input data for the support vector machine model could be easily extracted from sketches or the project's scope definition. The data were collected from contracts awarded by the Mayoralty of Baghdad for completed projects between 2010-2013. Mathematical equations were constructed using the Support Vector Machine Algorithm (SMO) technique. An average of accuracy (AA) (99.65%) and coefficient of determination (R 2 ) (97.63%) for the model was achieved by the created prediction equations.

show abstract

“…On the other hand, for BDA techniques such as statistics: data mining, Machine learning techniques, regression, classification and clustering are reported. The construction industry has employed some of these statistical methods in a variety of application areas, such as identifying causes of construction delays (Chau et al, 2003) learning from post-project reviews (PPRs) (Carrillo et al, 2011), decision support for construction litigation ( Jordan and Mitchell, 2015;Mahfouz, 2009), detecting structural damages of buildings ( Jiang and Mahadevan, 2008), identifying actions of workers and heavy machinery (Gong et al, 2011;Huang and Beck, 2013). Chau et al (2003) in their study of identifying critical factors for construction delays has employed data mining techniques to capture ML algorithms to produce knowledge discovery dataset (KDD).…”

Section: Data Synthesismentioning

confidence: 99%

Critical analysis for big data studies in construction: significant gaps in knowledge

Madanayake

Egbu

2019

BEPAM

View full text Add to dashboard Cite

Purpose The purpose of this paper is to identify the gaps and potential future research avenues in the big data research specifically in the construction industry. Design/methodology/approach The paper adopts systematic literature review (SLR) approach to observe and understand trends and extant patterns/themes in the big data analytics (BDA) research area particularly in construction-specific literature. Findings A significant rise in construction big data research is identified with an increasing trend in number of yearly articles. The main themes discussed were big data as a concept, big data analytical methods/techniques, big data opportunities – challenges and big data application. The paper emphasises “the implication of big data in to overall sustainability” as a gap that needs to be addressed. These implications are categorised as social, economic and environmental aspects. Research limitations/implications The SLR is carried out for construction technology and management research for the time period of 2007–2017 in Scopus and emerald databases only. Practical implications The paper enables practitioners to explore the key themes discussed around big data research as well as the practical applicability of big data techniques. The advances in existing big data research inform practitioners the current social, economic and environmental implications of big data which would ultimately help them to incorporate into their strategies to pursue competitive advantage. Identification of knowledge gaps helps keep the academic research move forward for a continuously evolving body of knowledge. The suggested new research avenues will inform future researchers for potential trending and untouched areas for research. Social implications Identification of knowledge gaps helps keep the academic research move forward for continuous improvement while learning. The continuously evolving body of knowledge is an asset to the society in terms of revealing the truth about emerging technologies. Originality/value There is currently no comprehensive review that addresses social, economic and environmental implications of big data in construction literature. Through this paper, these gaps are identified and filled in an understandable way. This paper establishes these gaps as key issues to consider for the continuous future improvement of big data research in the context of the construction industry.

show abstract

Construction legal support for differing site conditions (DSC) through statistical modeling and machine learning (ML)

Abstract: I would like to dedicate my doctorate research to my parents for their absolute love, care and support, my wife Lamia Moustafa for her full support and understanding, and my sons Youssef and Adam for all the joy that they bring to my life.

Cited by 4 publications

References 114 publications

Big Data in the construction industry: A review of present status, opportunities, and future trends

Big Data in the construction industry: A review of present status, opportunities, and future trends

Archives of Civil Engineering

Critical analysis for big data studies in construction: significant gaps in knowledge

Contact Info

Product

Resources

About