| Title |
Development of a hybrid artificial neural network method for evaluation of the sustainable construction projects |
| ID_Doc |
73916 |
| Authors |
Albasri, HW; Naimi, S |
| Title |
Development of a hybrid artificial neural network method for evaluation of the sustainable construction projects |
| Year |
2023 |
| Published |
Acta Logistica, 10, 3 |
| DOI |
10.22306/al.v10i3.378 |
| Abstract |
Planned methods may be developed to improve the efficiency of building construction. The construction business is profoundly impacted by the prevalence of inaccurate cost and schedule prediction. The main strategy to improve the project performance is to evaluate the hybrid sustainable materials using the artificial neural network (ANN) method based on the effective factors in construction projects in Iraq. This strategy needs an effective method to classify the project input representation and specify the accurate activity of each factor. This paper uses a hybrid artificial neural network to correlate and classify the sustainable hybrid of construction projects to evaluate their performance. The contribution of this method is the selection of the Multi-Criteria Decision-Maker method (MCDM) based on time and cost-effective factors correlated with the artificial neural network method. A dynamic selection procedure for project materials may be created using the existing technique as an evolutionary model for successful project completion. The MCDM observed that the appropriate sustainable material was considered as the main factor with a rank of 0.823 for cost effect and 0.735 for time effect and the main influence factor in Iraqi projects was the building height. The results present superior functional cost evaluation results correlated with the selection of hybrid sustainable materials. |
| Author Keywords |
construction management; sustainability; materials; artificial neural network; construction projects. |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Emerging Sources Citation Index (ESCI) |
| EID |
WOS:001108396600010 |
| WoS Category |
Engineering, Industrial; Management |
| Research Area |
Engineering; Business & Economics |
| PDF |
https://doi.org/10.22306/al.v10i3.378
|