Applied artificial intelligence for predicting construction projects delay

Egwim, Christian Nnaemeka; Alaka, Hafiz; Toriola-Coker, Luqman Olalekan; Balogun, Habeeb; Sunmola, Funlade

doi:10.1016/j.mlwa.2021.100166

Cited by 41 publications

(43 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar concerns were highlighted by others such as [32], who emphasized the inefficient and error-prone 'paper-based processes' used in site meetings, record keeping, works inspections, and monitoring, during which project deadline pressures could result in compromised accuracy or quality, hence contributing to delays. It was also shown that for an industry that is rich in data from sources such as BIM and Internet-of-Things (IoT) sensors in its project sites, the pace of adoption of artificial intelligence (AI) and machine learning (ML) for predicting and managing delays is slow [33]. One area where digital technology can support research into construction project delays is in understanding the synergy between delay factors.…”

Section: Literature Review 21 Construction Delays In Global Contextmentioning

confidence: 99%

Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects

Adamu

Alotaibi

2022

Buildings

View full text Add to dashboard Cite

In rapidly developing countries such as the Kingdom of Saudi Arabia (KSA), where the construction of buildings and supporting infrastructure is critical to achieving strategic developmental milestones, delays to capital projects can derail other sectors of the economy and could derail the Vision 2030 agenda. Attempts have been made over the years to explore the causes of construction project delays, including those in Saudi Arabia. Many of these studies are either outdated, narrow in scope, or tend to use only qualitative data, and not many have focused on the client-related delay factors affecting projects critical to Vision 2030. This study investigates client-related delay factors in terms of their correlation with key characteristics of recently completed construction projects in KSA. This objective necessitated the use of historical data; hence, an archival analysis was conducted for 37 projects among three different public sector ministries. The data were subjected to manual extraction, descriptive statistical analysis, and the use of established models such as schedule performance index (SPI) and cost performance index (CPI), and inferential (correlation) in Statistical Package for the Social Sciences (SPSS) using point-biserial correlation coefficient (rpb, where p > 0.05) to explore association and impact of project characteristics on themselves and on client-related causes of delay. Results revealed eight unique client-related causes of delay, with SPI values of 0.71 to 0.82, as well as CPI values ranging from 0.84 to 0.89, suggesting very poor time and cost performance across all projects, as well as the magnitude of correlation of key project characteristics (cost, duration, additional time, and additional cost) with the eight client-related causes of delay. The findings can help the client (authorities) understand and curb delays that are due to their own making, and it is recommended that such delay factors, whose likelihood are now established and whose potential impact can be measured against key project characteristics, be developed into a delay risk impact tool. International joint ventures can bring technical expertise for Vision 2030, but they cannot eliminate delays due to government practices.

show abstract

Section: Literature Review 21 Construction Delays In Global Contextmentioning

confidence: 99%

Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects

Adamu

Alotaibi

2022

Buildings

View full text Add to dashboard Cite

show abstract

“…Various types of Machine Learning (ML) such as (GA), Neural Network (NN), Linear Regression, Logistic Regression, Nearest-Neighbor Mapping, Decision Trees, K-Means Clustering, Random Forests, and Support Vector Machines exist for ML model implementation [9]. Several factors needed to be considered when choosing ML to be used in training time, accuracy, and so on.…”

Section: Literature Reviewmentioning

confidence: 99%

“…A projected amount of 15% of global gross domestic product (GDP) was on the rise in 2020 compared to 13% of global GDP in 2017 which was gotten from the global construction industry surveyed by McKinsey Global Institute survey during their conducted exercise in 2017 [8]. Considering construction sector as one of the major contributor to the world economy representing 13% of the global GDP with a promising 85% to $15.5 billion globally by the year 2030 with three leading countries -China, the United States and Indiacontributing 57% of its global demand [9]. Moreover world's technology leaders and governments around the world should continue to put in more effort into the implementation of AI in order to gain a competitive advantage [10].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence Systems for Teaching and Learning in Civil Engineering: Conceptual Framework

Coker¹,

AYekini²,

Alaka³

et al. 2022

Artificial Intelligence Trends &Amp; Technologies

View full text Add to dashboard Cite

Artificial intelligence technology is based on design of machine or computer application that mimic human intelligent. Use of artificial intelligence in teaching and learning in civil engineering is a welcome development. This paper presents a conceptual framework of Artificial Intelligence Systems for Teaching, Learning, and administration of in Civil Engineering education. The proposed system is to be designed using the following tools: Extensible Markup Language (XML) to develop the GUI, Hypertext Pre-processor (PHP) for the web user interface (WUI), APACHE for middleware, MYSQL for database design, and UML will be used to visualize the design of the system. If the system is developed and implemented, it will go a long way to advance teaching and learning, and educational administration in civil engineering profession.

show abstract

“…Moon et al (2014) developed an active simulation system based on 4D models and an optimisation process to minimise the simultaneous interference level of the schedule-workspace; 3) monitoring construction work progress: Tran et al (2020) explored the use of 4D BIM and visual programming to develop a conceptual framework of camera planning that enables the monitoring of construction site progress. Braun et al (2015) proposed an automated framework based on photogrammetric surveys and 4D BIM models to detect deviations in the construction process between the actual state of a construction and its planned state; 4) producing short-term work plans: Sriprasert and Dawood (Sriprasert and Dawood, 2022) implemented the LEWIS system; a visual multi-constraints planning framework based on the use of 4D BIM and Lean methodology principles, to enable integrating construction related information and constraints with 4D BIM; 5) managing construction health and safety: Tran et al (2021) proposed a hazard identification approach based on 4D BIM and spatial-temporal conflicts potentially leading to accidents, to prevent construction accidents. Han et al (2017) proposed the 3D-CES system to analyse 3D-based visualisation of mobile crane operation.…”

Section: Construction Planning and The Advent Of 4d Building Informat...mentioning

confidence: 99%

The efficient generation of 4D BIM construction schedules: A case study of the Nanterre 2 CESI project in France

Doukari

Seck²,

Greenwood³

2022

Front. Built Environ.

View full text Add to dashboard Cite

Building Information Modelling (BIM) can be defined as a set of tools, processes and technologies that are enabled by a digital multi-dimensional representation of the physical and functional characteristics of a built asset. The ‘fourth’ dimension (4D BIM) incorporates time-related project information in the 3D model to simulate and optimise the project construction process. To achieve this, the 3D objects within the aggregated design model must be linked with each activity in the construction schedule. However, the levels of maturity and expertise in using BIM amongst the project participants still varies considerably. This generates collaboration problems within the project and adds further obstacles to the ability to derive full benefits from BIM. Ideally, 4D BIM can be automatically generated, but in reality, because the 3D and 4D models are created separately and at different stages of the project, this is not currently possible, and the process requires considerable manual effort. The research reported in this paper was prompted by the construction of a new training and research building: the Nanterre 2 CESI building in France. It proposes an efficient approach that minimises the effort of creating 4D BIM construction schedules. The CESI four-phase process aims to help project participants to fully exploit the potential of 4D BIM and enables: 1) a clear expression of the 4D BIM objectives; 2) the identification of information requirements and relevant workflows to achieve these objectives; 3) the implementation of a project schedule; and 4) BIM model production to suit the 4D BIM use case. Although the CESI approach was developed in the context of the French contracting system, the observations and conclusions of this study are intended to be generally applicable.

show abstract

Applied artificial intelligence for predicting construction projects delay

Cited by 41 publications

References 19 publications

Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects

Exploring the Nature and Impact of Client-Related Delays on Contemporary Saudi Construction Projects

Artificial Intelligence Systems for Teaching and Learning in Civil Engineering: Conceptual Framework

The efficient generation of 4D BIM construction schedules: A case study of the Nanterre 2 CESI project in France

Contact Info

Product

Resources

About