Risk source-based constructability appraisal using supervised machine learning

Kifokeris, Dimosthenis; Xenidis, Yiannis

doi:10.1016/j.autcon.2019.04.012

Cited by 15 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The utilization of ML involves a computer system calculation that addresses problems intelligently by imitating the thought process of the human brain [50] in solving prediction or classification issues [51]. In ML, many algorithms and technologies, such as DT, ANN, and SVM, have been used to execute prediction tasks and classification models [52,53]. Classification and regression are used to acquire a group of models by training information, and the model can be applied to predict the group category of unclassified data.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Classification for Project Features with Machine Learning Algorithms

Fan

2022

Symmetry

View full text Add to dashboard Cite

Due to the asymmetry of project features, it is difficult for project managers to make a reliable prediction of the decision-making process. Big data research can establish more predictions through the results of accurate classification. Machine learning (ML) has been widely applied for big data analytic and processing, which includes model symmetry/asymmetry of various prediction problems. The purpose of this study is to achieve symmetry in the developed decision-making solution based on the optimal classification results. Defects are important metrics of construction management performance. Accordingly, the use of suitable algorithms to comprehend the characteristics of these defects and train and test massive data on defects can conduct the effectual classification of project features. This research used 499 defective classes and related features from the Public Works Bid Management System (PWBMS). In this article, ML algorithms, such as support vector machine (SVM), artificial neural network (ANN), decision tree (DT), and Bayesian network (BN), were employed to predict the relationship between three target variables (engineering level, project cost, and construction progress) and defects. To formulate and subsequently cross-validate an optimal classification model, 1015 projects were considered in this work. Assessment indicators showed that the accuracy of ANN for classifying the engineering level is 93.20%, and the accuracy values of SVM for classifying the project cost and construction progress are 85.32% and 79.01%, respectively. In general, the SVM yielded better classification results from these project features. This research was based on an ML algorithm evaluation system for buildings as a classification model for project features with the goal of aiding project managers to comprehend defects.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluation of Classification for Project Features with Machine Learning Algorithms

Fan

2022

Symmetry

View full text Add to dashboard Cite

show abstract

“…Participants were motivated by prospects of salary, networking, and experience. (Kifokeris & Xenidis, 2019) Development of a framework to evaluate the constructability of a project with known risks using supervised machine learning Creation of an accurate classifying equation for forecasting the constructability of a project integrating risk analysis (Kovtun et al, 2020) Consideration of information risks for developing loyalty programs for megaprojects Convolutional neural networks were capable of risk analysis with higher accuracy, thus more suitable for loyalty programs, (Lobo & Abid, 2020) Analysis of impact on public and resistance to a railway megaproject via social media Recommended to utilize social media marketing principles for enhancing relationships among stakeholders (Natarajan, 2022) Use of machine learning for predicting cost and schedule overruns in oil and gas megaprojects…”

Section: Challenges Of Implementing Digital Tools In Megaprojectsmentioning

confidence: 99%

Data Analytics and Artificial Intelligence in the Complex Environment of Megaprojects: Implications for Practitioners and Project Organizing Theory

Wijayasekera

Hussain

Paudel

et al. 2022

Project Management Journal

View full text Add to dashboard Cite

This article articulates the prospect of improving megaproject execution and performance via digital project delivery. Various digitalization options, such as cloud computing, automation, artificial intelligence, information modeling, and data analytics and their recent usage in megaprojects, are critically reviewed. Prospective future developments and forthcoming challenges of digitalization in megaprojects have also been identified based on the current progress of these technologies. In terms of theory, we suggest information economics and organizational economics as a starting place to develop a research approach to artificial intelligence and megaprojects.

show abstract

“…However, with artificial intelligence, there might be a greater influence of technology in the construction sector for human errors mitigation. Nowadays, contractors are continuously gathering data on accidents taking place in the construction site, so machine learning can be used to find underlying patterns in the collected data and prevent accidents (engineering .com, 2019;Kifokeris & Xenidis, 2019;Maskin entreprenoren, 2020). Nevertheless, other technological advancements are already playing an important role in this matter these days, through technologies such as Building Information Modelling Technology, 3D printing, Virtual…”

Section: Human Error Mitigationmentioning

confidence: 99%

Human Error–Induced Risk in Reinforced Concrete Bridge Engineering

Galvão

Matos

Oliveira

2021

J. Perform. Constr. Facil.

View full text Add to dashboard Cite

Throughout the last century and in recent years, several bridge failures have taken place worldwide. Recent studies uncovered that the primary cause of these collapses were human errors in design, construction and operation phases. Regardless of this finding, there is still a considerable gap between this information and the known errors and the risk they represent for structural safety. Aiming for a better understanding of human errors, an identification procedure and a qualitative assessment of such errors considering risk-based indicators (probability of occurrence and consequence) was performed. Several brainstorming meetings with design and construction experts led to the identification of 49 relevant human errors, which were listed for further evaluation on a survey. Much more important than identifying and assessing these errors is identifying those that pose a greater threat to safety. Using a decision-making tool (Analytical Hierarchy Process) to process all the information collected in the survey, the errors were ranked according to risk indicators. Furthermore, a qualitative risk assessment is performed, allowing the identification of the errors denoting higher risk for structural safety, according to experts' opinions.

show abstract

Risk source-based constructability appraisal using supervised machine learning

Cited by 15 publications

References 37 publications

Evaluation of Classification for Project Features with Machine Learning Algorithms

Evaluation of Classification for Project Features with Machine Learning Algorithms

Data Analytics and Artificial Intelligence in the Complex Environment of Megaprojects: Implications for Practitioners and Project Organizing Theory

Human Error–Induced Risk in Reinforced Concrete Bridge Engineering

Contact Info

Product

Resources

About