Enhanced Construction Project Duration Estimation Using Artificial Neural Networks: Initial Design and Planning Stages
Article Sidebar
Main Article Content
Abstract
Maintaining efficiency and quality control during the early phases of construction projects depends on accurate duration estimation. However, because there is not enough data available in the initial stages of project planning, traditional methodologies suffer. To address these challenges, this study presents an innovative approach using artificial neural networks (ANNs) through Python. This method offers reliable predictions for early-stage duration estimation. ANN models were created and validated with 53 design parameters using data from 100 different construction projects in Jordan. Furthermore, the study refined the models to 43 parameters using a questionnaire-driven approach. The average duration estimation accuracy of the ANN models was 90% during the initial stage and 95% during the planning stage, demonstrating their great accuracy. Its uniqueness comes in its application of ANN to early-stage building, an area that has not been extensively studied in the literature to date, and in its demonstration that reliable predictions may be generated in the absence of abundant data. This study demonstrates ANN's effectiveness in enhancing early-stage construction planning by providing stakeholders with a more accurate duration estimation tool than traditional methods. The findings contribute significantly to improving decision-making and project planning in the early phases.
Article Details
Section
Authors who publish with this journal agree to the following terms:
a) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share and adapt the work with an acknowledgement of the work's authorship and initial publication in this journal.
b) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
c) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Open Access Citation Advantage Service). Where authors include such a work in an institutional repository or on their website (ie. a copy of a work which has been published in a UTS ePRESS journal, or a pre-print or post-print version of that work), we request that they include a statement that acknowledges the UTS ePRESS publication including the name of the journal, the volume number and a web-link to the journal item.
d) Authors should be aware that the Creative Commons Attribution (CC-BY) License permits readers to share (copy and redistribute the work in any medium or format) and adapt (remix, transform, and build upon the work) for any purpose, even commercially, provided they also give appropriate credit to the work, provide a link to the license, and indicate if changes were made. They may do these things in any reasonable manner, but not in any way that suggests you or your publisher endorses their use.