Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 11 (2022) > Article

DOI: 10.14704/nq.2022.20.11.NQ66157

COST ESTIMATION USING COMPUTATIONAL INTELLIGENCE

SARAH ALAA MOHAMMED ALMOUSAWI,EHSAN JAHANI,NASER KORDANI

Abstract

Nowadays, accurate cost estimation at an early stage plays an essential role in any initial construction, as it affects the project's success, and underestimation may lead to project failure in terms of costs. It may lead to the loss of the project or its closure due to the unavailability of cost despite the limited design data available at that stage. This research aims to estimate the cost of various construction projects by developing a cost estimation technique with the least possible losses. Where collected data for 360 distinctive buildings. In addition, discover many relevant cost criteria. In this research, three algorithms Artificial Neural Network (ANN) model method and the Long Short-Term Memory method (LSTM), and used Matlab and Microsoft Excel Solver to create a network model analysis nervousness; The accuracy of these models, such as those generated by LSTM, and ANN is ultimately determined by a realistic estimated value. The ANN and LSTM were reasonably successful in estimating the early stages of construction pricing using basic projects without needing a more comprehensive design. The best version of the advanced neural version is represented by (LSTM), where the accuracy reached (99.21%), (99.26%) for models (A) and (B), and followed by the results obtained from the ordinary neural networks in the (The Bayesian regularization algorithm) algorithm. The ANN model II and I managed to achieve average accuracy percentages of (99.98%) and (99.94%) for model (A) and (99.89%) and (99.65%) for model (B), respectively.

Keywords

Artificial Neural Networks (ANN), multiple regression, Long Short-Term Memory (LSTM), early cost, estimation cost.

Full Text

PDF

References

?>